Browse by library¶
Declared in extracted details¶
Values reported by the structured extraction (field libraries).
- SEAL (52): SoK: Private LLM Inference using Approximate Homomorphic Encryption; Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; MOAI: Module-optimizing architecture for non-interactive secure transformer inference; Secure transformer inference made non-interactive; STIP: Efficient and secure non-interactive transformer inference via compact packing; ENSI: Efficient non-interactive secure inference for large language models; Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption; On the Security of Homomorphic Encryption on Approximate Numbers; Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference; High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function; PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption; Delphi: A Cryptographic Inference Service for Neural Networks; CrypTFlow2: Practical 2-Party Secure Inference; Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference; THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption; Iron: Private Inference on Transformers; CipherGPT: Secure Two-Party GPT Inference; BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers; BumbleBee: Secure Two-party Inference Framework for Large Transformers; HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data; Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library; EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation; TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption; HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0; BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption; Secure federated learning applied to medical imaging with fully homomorphic encryption; Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs; Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption; Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption; Secure human action recognition by encrypted neural network inference; Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network; Fully Homomorphically Encrypted Deep Learning as a Service; Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption; Homomorphic Encryption for Machine Learning and Artificial Intelligence Applications; Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference; Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning; A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption; A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities; Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics; COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025; Fully Homomorphic Encryption for Cyclotomic Prime Moduli; ModHE: Modular Homomorphic Encryption Using Module Lattices: Potentials and Limitations; Pasta: A Case for Hybrid Homomorphic Encryption; Approximate homomorphic encryption based privacy-preserving machine learning: a survey; Privft: Private and fast text classification with homomorphic encryption; SoK: Privacy-preserving computation techniques for deep learning; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions; SPIRAL: Fast, high-rate single-server PIR via FHE composition; Security guidelines for implementing homomorphic encryption; Secure outsourced matrix computation and application to neural networks; Homomorphic encryption standard
- OpenFHE (25): SoK: Private LLM Inference using Approximate Homomorphic Encryption; EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption; ENSI: Efficient non-interactive secure inference for large language models; THEMIS: A Co-Designed System for Encrypted Transformer Inference; High-Precision Functional Bootstrapping for CKKS from Fourier Extension; Fully Homomorphic Encryption for Matrix Arithmetic; Trace-Factored BigSwitch for Matrix-Friendly FHE; OpenFHE: Open-Source Fully Homomorphic Encryption Library; FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs; HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0; TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation; Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption; Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption; Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; The Power of Low Rank: Fast CKKS Functional Bootstrapping for High-Precision Lookup Tables; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption; LFHE: Fully Homomorphic Encryption with Bootstrapping Key Size Less than a Megabyte; FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext; High-Precision Homomorphic ALU over Arbitrary Moduli with O (1) Bootstrapping; Revisiting Shamir Secret Sharing for Threshold Fully Homomorphic Encryption; Private svm inference on encrypted data; Demystifying bootstrapping in fully homomorphic encryption; Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives; Security guidelines for implementing homomorphic encryption; Secure numerical simulations using fully homomorphic encryption
- Lattigo (23): SoK: Private LLM Inference using Approximate Homomorphic Encryption; Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache; ARION: Attention-optimized transformer inference on encrypted data; ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation; Securing Approximate Homomorphic Encryption Using Differential Privacy; Multiparty Homomorphic Encryption from Ring-Learning-with-Errors; Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-Sparse Keys; Accelerating HE Operations from Key Decomposition Technique; Efficient Bootstrapping in Fully Homomorphic Encryption for Matrix Arithmetic; Orion: A Fully Homomorphic Encryption Framework for Deep Learning; ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse; Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption; Bootstrapping for Approximate Homomorphic Encryption with Negligible Failure-Probability by Using Sparse-Secret Encapsulation; XBOOT: Free-XOR Gates for CKKS with Applications to Transciphering; Efficient Homomorphic Integer Computer from CKKS; Stay in Your Lane: Fast Arithmetic over Large Finite Rings with CKKS; Bootstrapping GBFV with CKKS; Revisiting Shamir Secret Sharing for Threshold Fully Homomorphic Encryption; Transciphering Framework for Approximate Homomorphic Encryption; Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version); Cryptanalysis of Symmetric Primitives over Rings and a Key Recovery Attack on Rubato; The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption; Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives
- HElib (20): On the Security of Homomorphic Encryption on Approximate Numbers; Securing Approximate Homomorphic Encryption Using Differential Privacy; FHEW: Bootstrapping Homomorphic Encryption in Less Than a Second; OpenFHE: Open-Source Fully Homomorphic Encryption Library; Algorithms in HElib; F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption; DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption; Private machine learning classification based on fully homomorphic encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities; Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics; Transciphering Framework for Approximate Homomorphic Encryption; Pasta: A Case for Hybrid Homomorphic Encryption; Rasta: A cipher with low ANDdepth and few ANDs per bit; Stream ciphers: A Practical Solution for Efficient Homomorphic-Ciphertext Compression; Demystifying bootstrapping in fully homomorphic encryption; SoK: Privacy-preserving computation techniques for deep learning; Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives; SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training; Homomorphic encryption standard
- PyTorch (14): CrypTen: Secure Multi-Party Computation Meets Machine Learning; SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference; Orion: A Fully Homomorphic Encryption Framework for Deep Learning; DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption; TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption; Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach; Secure federated learning applied to medical imaging with fully homomorphic encryption; Secure human action recognition by encrypted neural network inference; Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models; fairseq: A fast, extensible toolkit for sequence modeling; [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md); Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage; ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
- PALISADE (13): Approximate Homomorphic Encryption with Reduced Approximation Error; On the Security of Homomorphic Encryption on Approximate Numbers; Securing Approximate Homomorphic Encryption Using Differential Privacy; Revisiting Homomorphic Encryption Schemes for Finite Fields; OpenFHE: Open-Source Fully Homomorphic Encryption Library; TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation; FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System; A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption; Large-Plaintext Functional Bootstrapping in FHE with Small Bootstrapping Keys; Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption; Homomorphic encryption standard
- HEAAN (12): Homomorphic Encryption for Arithmetic of Approximate Numbers; A Full RNS Variant of Approximate Homomorphic Encryption; On the Security of Homomorphic Encryption on Approximate Numbers; Bootstrapping for Approximate Homomorphic Encryption; Improved Bootstrapping for Approximate Homomorphic Encryption; OpenFHE: Open-Source Fully Homomorphic Encryption Library; F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities; Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics; On the precision loss in approximate homomorphic encryption; Homomorphic encryption standard
- Phantom (11): SoK: Private LLM Inference using Approximate Homomorphic Encryption; Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache; Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; MOAI: Module-optimizing architecture for non-interactive secure transformer inference; Secure transformer inference made non-interactive; STIP: Efficient and secure non-interactive transformer inference via compact packing; ENSI: Efficient non-interactive secure inference for large language models; ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation; Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library; FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs; Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures
- CUDA (9): Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference; Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study; zkLLM: Zero Knowledge Proofs for Large Language Models; Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library; FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs; Over 100x Faster Bootstrapping in Fully Homomorphic Encryption through Memory-centric Optimization with GPUs; HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0; TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU; Privft: Private and fast text classification with homomorphic encryption
- HEaaN (8): SoK: Private LLM Inference using Approximate Homomorphic Encryption; Encryption-friendly LLM architecture; Bootstrapping Bits with CKKS; Leveraging Discrete CKKS to Bootstrap in High Precision; Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused; SHIP: A Shallow and Highly Parallelizable CKKS Bootstrapping Algorithm; Fast and Accurate Homomorphic Softmax Evaluation; DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption
- Concrete (6): BLEACH: Cleaning Errors in Discrete Computations over CKKS; Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks; Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption; HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models; Towards Case-Optimized Hybrid Homomorphic Encryption; Security guidelines for implementing homomorphic encryption
- EMP-toolkit (6): CrypTFlow2: Practical 2-Party Secure Inference; Iron: Private Inference on Transformers; BumbleBee: Secure Two-party Inference Framework for Large Transformers; MP-SPDZ: A Versatile Framework for Multi-Party Computation; Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption; Ajax: Fast Threshold Fully Homomorphic Encryption without Noise Flooding
- TenSEAL (6): TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption; Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach; Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication; FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System; HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models; Approximate homomorphic encryption based privacy-preserving machine learning: a survey
- TFHE (6): Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities; Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics; Fully Homomorphic Encryption for Machine Learning; Pasta: A Case for Hybrid Homomorphic Encryption; Homomorphic encryption standard
- TFHE-rs (5): TFHE Gets Real: An Efficient and Flexible Homomorphic Floating-Point Arithmetic; Efficient Homomorphic Integer Computer from CKKS; SWIFT: Shallow and SIMD-Aware CKKS Functional Bootstrapping for Low-Latency; FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext; Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives
- CrypTen (4): MPCFormer: Fast, Performant and Private Transformer Inference with MPC; SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; CrypTen: Secure Multi-Party Computation Meets Machine Learning; SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning
- Concrete ML (3): A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference; Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption; Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning
- CUTLASS (3): SIGMA: Secure GPT Inference with Function Secret Sharing; TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU; ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
- FIDESlib (3): SoK: Private LLM Inference using Approximate Homomorphic Encryption; ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference; HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation
- Flower (3): Federated Learning: An approach with Hybrid Homomorphic Encryption; BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption; Secure federated learning applied to medical imaging with fully homomorphic encryption
- HuggingFace Transformers (3): EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption; MOAI: Module-optimizing architecture for non-interactive secure transformer inference; MPCFormer: Fast, Performant and Private Transformer Inference with MPC
- Intel HEXL (3): OpenFHE: Open-Source Fully Homomorphic Encryption Library; FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext; SPIRAL: Fast, high-rate single-server PIR via FHE composition
- lattice-estimator (3): SWIFT: Shallow and SIMD-Aware CKKS Functional Bootstrapping for Low-Latency; The Power of Low Rank: Fast CKKS Functional Bootstrapping for High-Precision Lookup Tables; Multi-key Fully Homomorphic Encryption with Non-Interactive Setup in the Plain Model
- NTL (3): Homomorphic Encryption for Arithmetic of Approximate Numbers; Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs; Fully Homomorphic Encryption with Relatively Small Key and Ciphertext Sizes
- scikit-learn (3): Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption; Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption; Private svm inference on encrypted data
- SecretFlow-SPU (3): PUMA: Secure Inference of LLaMA-7B in Five Minutes; Ditto: Quantization-aware Secure Inference of Transformers upon MPC; SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning
- cuHE (2): Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities; Homomorphic encryption standard
- EMP-tool (2): Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference; COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025
- EzPC (2): CrypTFlow2: Practical 2-Party Secure Inference; Iron: Private Inference on Transformers
- FHE-MP-CNN (2): MOAI: Module-optimizing architecture for non-interactive secure transformer inference; Secure transformer inference made non-interactive
- FullRNS-HEAAN (2): A Full RNS Variant of Approximate Homomorphic Encryption; On the precision loss in approximate homomorphic encryption
- GMP (2): Homomorphic Encryption for Arithmetic of Approximate Numbers; CHIMERA: Combining Ring-LWE-based Fully Homomorphic Encryption Schemes
- HE-transformer (2): THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
- HeLayers (2): BLEACH: Cleaning Errors in Discrete Computations over CKKS; HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
- HEXL (2): Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference; CipherGPT: Secure Two-Party GPT Inference
- Hugging Face Transformers (2): Ditto: Quantization-aware Secure Inference of Transformers upon MPC; SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference
- JAX (2): SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning; Neuracrypt is not private
- Lattice Estimator (2): Fully Homomorphic Encryption on the Ring of Gaussian Periods; Security guidelines for implementing homomorphic encryption
- llama.cpp (2): PrivateLoRA for Efficient Privacy Preserving LLM; Large language model inference acceleration: A comprehensive hardware perspective
- MP-SPDZ (2): SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning; MP-SPDZ: A Versatile Framework for Multi-Party Computation
- ONNX (2): Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering; HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models
- OpenBLAS (2): Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused; Low-Depth Bootstrapping for Matrix-Native FHE
- Pyfhel (2): BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- SageMath (2): Fully Homomorphic Encryption on the Ring of Gaussian Periods; Revisiting Module Lattice-based Homomorphic Encryption and Application to Secure-MPC
- Sollya (2): Encryption-friendly LLM architecture; Fast and Accurate Homomorphic Softmax Evaluation
- tensor2tensor (2): Attention is all you need; BERT: Pre-training of deep bidirectional transformers for language understanding
- TF Encrypted (2): SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning; SoK: Privacy-preserving computation techniques for deep learning
- TFHE library (2): CHIMERA: Combining Ring-LWE-based Fully Homomorphic Encryption Schemes; Multi-Key Homomorphic Encryption from TFHE
- TinyGarble2.0 (2): Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference; COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025
- A*HE (1): Privft: Private and fast text classification with homomorphic encryption
- ABY (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- ABY3 (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- AFV (GPU-accelerated BFV) (1): Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs
- Armadillo compiler (FV) (1): Stream ciphers: A Practical Solution for Efficient Homomorphic-Ciphertext Compression
- AutoGPTQ (1): PrivateLoRA for Efficient Privacy Preserving LLM
- axlearn (1): Theory, analysis, and best practices for sigmoid selfattention
- bitsandbytes (1): Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study
- bRPC (1): SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning
- Charm (1): Non-interactive Fully Encrypted Machine Learning Protocol for Inference
- chebfun (1): Efficient Homomorphic Evaluation on Large Intervals
- Cheddar (baseline GPU library) (1): A scalable multi-GPU framework for encrypted large-model inference
- CHET (1): EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
- Concrete ML (baseline) (1): Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
- Concrete ML 1.4.1 (1): Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering
- cryptoTools (1): SIGMA: Secure GPT Inference with Function Secret Sharing
- cuFHE (1): Homomorphic encryption standard
- custom C++ RNS-CKKS implementation (1): Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS
- DeepSpeed-Inference (1): ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
- desilofhe (1): CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption
- EasyFHE (1): An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference
- EMP toolkit (1): Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference
- EMP-OT (1): Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference
- EVA (1): Security guidelines for implementing homomorphic encryption
- EzPC (GPU-MPC) (1): SIGMA: Secure GPT Inference with Function Secret Sharing
- fairseq (1): fairseq: A fast, extensible toolkit for sequence modeling
- fancy-garbling (1): Delphi: A Cryptographic Inference Service for Neural Networks
- FasterTransformer (1): ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
- fastText (1): Privft: Private and fast text classification with homomorphic encryption
- FedML (1): FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System
- FFTW (1): FHEW: Bootstrapping Homomorphic Encryption in Less Than a Second
- FFTW.jl (1): Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
- fhe-textbook (educational Python demo library) (1): The Beginner's Textbook for Fully Homomorphic Encryption
- FHSVM (1): Private svm inference on encrypted data
- FlashAttention2 (extended) (1): Theory, analysis, and best practices for sigmoid selfattention
- Flax (1): PUMA: Secure Inference of LLaMA-7B in Five Minutes
- FLINT (1): Fully Homomorphic Encryption for Matrix Arithmetic
- ftfy (1): Improving language understanding by generative pretraining
- Gazelle HE library (own) (1): GAZELLE: A Low Latency Framework for Secure Neural Network Inference
- Gloo (1): CrypTen: Secure Multi-Party Computation Meets Machine Learning
- Go (1): The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption
- GPTQ (1): PrivateLoRA for Efficient Privacy Preserving LLM
- Graph Feature Preprocessor (GFP) (1): Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering
- HElayers (1): Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives
- HEonGPU (1): HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0
- HIENAA.jl (1): Multi-key Fully Homomorphic Encryption with Non-Interactive Setup in the Plain Model
- HuggingFace (1): ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
- Hummingbird (1): Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption
- hybrid-HE-framework (1): HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0
- hybrid-HE-framework (PASTA authors' C++ framework) (1): Federated Learning: An approach with Hybrid Homomorphic Encryption
- Julia (1): Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
- Keras (1): Fully Homomorphic Encryption for Machine Learning
- Liberate (1): SoK: Private LLM Inference using Approximate Homomorphic Encryption
- liberate-fhe (1): Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Liberate.FHE (1): THOR: Secure transformer inference with homomorphic encryption
- Liberate.FHE (GPU) (1): Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption
- libOTe (1): ABY3: A Mixed Protocol Framework for Machine Learning
- LM-Eval Harness (1): PrivateLoRA for Efficient Privacy Preserving LLM
- lm-evaluation-harness (1): EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
- LWE Estimator (1): Multi-Key Homomorphic Encryption from TFHE
- Magma (1): Bootstrapping for BGV and BFV Revisited
- MLIR (1): SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning
- MockSEAL (1): Private and reliable neural network inference
- MPyC (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- NCCL (1): fairseq: A fast, extensible toolkit for sequence modeling
- NEXUS-EndtoEnd (extended codebase) (1): ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
- NFLlib (1): Homomorphic encryption standard
- NNlib.jl (1): Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
- NumPy (1): Fully Homomorphically Encrypted Deep Learning as a Service
- Obliv-C (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- ObliVM (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- OpenBumbleBee (1): Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- OpenFHE (parameter sets revisited) (1): Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS
- OpenFHE.jl (1): Secure numerical simulations using fully homomorphic encryption
- OpenMP (1): MOAI: Module-optimizing architecture for non-interactive secure transformer inference
- OpenPEGASUS (1): Efficient Homomorphic Evaluation on Large Intervals
- OpenPegasus (1): Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version)
- OpenSSL (1): Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version)
- Orion (baseline) (1): Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
- PEFT (1): PrivateLoRA for Efficient Privacy Preserving LLM
- Permutations.jl (1): Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
- PICCO (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- Primus-FHE (1): Ajax: Fast Threshold Fully Homomorphic Encryption without Noise Flooding
- Protocol Buffers (1): EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
- pybind11 (1): Federated Learning: An approach with Hybrid Homomorphic Encryption
- python-paillier (1): Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives
- python-reseal (ReSeal) (1): Fully Homomorphically Encrypted Deep Learning as a Service
- RNS-HEAAN (1): On the Security of Homomorphic Encryption on Approximate Numbers
- Rust (1): Towards Case-Optimized Hybrid Homomorphic Encryption
- SCALE-MAMBA (1): MP-SPDZ: A Versatile Framework for Multi-Party Computation
- SCI (CrypTFlow2) (1): Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference
- SCI (EzPC) (1): BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers
- SEAL 3.6.6 (1): Private and reliable neural network inference
- SEAL-Python (1): Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption
- SealPIR (1): HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0
- SecretFlow SPU (1): Nimbus: Secure and Efficient Two-Party Inference for Transformers
- SecureArithmetic.jl (1): Secure numerical simulations using fully homomorphic encryption
- SIRNN (EzPC) (1): CipherGPT: Secure Two-Party GPT Inference
- spaCy (1): Improving language understanding by generative pretraining
- SPIRAL (1): TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation
- SPU (BumbleBee BOLE code) (1): CipherGPT: Secure Two-Party GPT Inference
- TensorFlow (1): TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption
- TensorFlow XLA (1): ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
- Tensorpack (1): Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs
- TFHE (tfhe/tfhe) (1): TFHE: Fast Fully Homomorphic Encryption over the Torus
- tfhe-rs (1): Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- TorchTitan (1): Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage
- TurboTransformer (1): ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
- vLLM (1): Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study
- WarpDrive (1): Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures
- xformers (1): Llama: Open and efficient foundation language models
- XGBoost (1): Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering
- XKCP (1): Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version)
- YACL (1): BumbleBee: Secure Two-party Inference Framework for Large Transformers
Mentions in full text¶
Papers ordered by how often the term occurs (count in brackets). Only papers with a local PDF are counted.
Microsoft SEAL (97 papers)¶
Pasta: A Case for Hybrid Homomorphic Encryption (59), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (43), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (25), Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (24), COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025 (19), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (18), ARION: Attention-optimized transformer inference on encrypted data (18), Privft: Private and fast text classification with homomorphic encryption (17), Better Bootstrapping for Approximate Homomorphic Encryption (17), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (16), Security guidelines for implementing homomorphic encryption (15), SoK: Private LLM Inference using Approximate Homomorphic Encryption (15), Private and reliable neural network inference (14), SoK: Private transformer-based model inference (14), On the Security of Homomorphic Encryption on Approximate Numbers (14), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (12), Secure federated learning applied to medical imaging with fully homomorphic encryption (12), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (10), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (10), High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function (10), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (9), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (9), Fully Homomorphic Encryption for Cyclotomic Prime Moduli (9), Fully Homomorphically Encrypted Deep Learning as a Service (9), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (9), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (9), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (8), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (8), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (7), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (6), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (6), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (6), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (6), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (6), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (6), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (6), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (5), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (5), BumbleBee: Secure Two-party Inference Framework for Large Transformers (5), CrypTFlow2: Practical 2-Party Secure Inference (5), Delphi: A Cryptographic Inference Service for Neural Networks (5), Revisiting Homomorphic Encryption Schemes for Finite Fields (5), Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-Sparse Keys (5), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (4), Fully Homomorphic Encryption for Machine Learning (4), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (4), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (4), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (4), TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption (4), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (4), Approximate Homomorphic Encryption with Reduced Approximation Error (4), ENSI: Efficient non-interactive secure inference for large language models (4), Homomorphic encryption standard (3), Secure outsourced matrix computation and application to neural networks (3), Secure numerical simulations using fully homomorphic encryption (3), SPIRAL: Fast, high-rate single-server PIR via FHE composition (3), SoK: Privacy-preserving computation techniques for deep learning (3), Relaxed Functional Bootstrapping: A New Perspective on BGV/BFV Bootstrapping (3), CKKS Bootstrapping in less than 10ms (3), Homomorphic Encryption for Machine Learning and Artificial Intelligence Applications (3) …
HElib (94 papers)¶
Pasta: A Case for Hybrid Homomorphic Encryption (63), Private machine learning classification based on fully homomorphic encryption (38), On the Security of Homomorphic Encryption on Approximate Numbers (21), BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption (19), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (18), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (12), Algorithms in HElib (12), Fully Homomorphic Encryption for Machine Learning (11), The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption (10), OpenFHE: Open-Source Fully Homomorphic Encryption Library (9), Bootstrapping for BGV and BFV Revisited (8), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (8), Towards Case-Optimized Hybrid Homomorphic Encryption (7), Revisiting Homomorphic Encryption Schemes for Finite Fields (7), Stream ciphers: A Practical Solution for Efficient Homomorphic-Ciphertext Compression (6), Fully Homomorphic Encryption for Cyclotomic Prime Moduli (6), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (6), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (6), FHEW: Bootstrapping Homomorphic Encryption in Less Than a Second (6), Securing Approximate Homomorphic Encryption Using Differential Privacy (6), A comprehensive survey on secure outsourced computation and its applications (5), Rasta: A cipher with low ANDdepth and few ANDs per bit (5), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (5), Homomorphic encryption standard (4), On the precision loss in approximate homomorphic encryption (4), Demystifying bootstrapping in fully homomorphic encryption (4), Transciphering Framework for Approximate Homomorphic Encryption (4), Relaxed Functional Bootstrapping: A New Perspective on BGV/BFV Bootstrapping (4), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (4), Approximate Homomorphic Encryption with Reduced Approximation Error (4), Secure numerical simulations using fully homomorphic encryption (3), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), SoK: Private transformer-based model inference (3), Generalized BGV, BFV, and CKKS for Homomorphic Encryption over Matrix Rings (3), Ring packing and amortized FHEW bootstrapping (3), The Beginner's Textbook for Fully Homomorphic Encryption (3), Over 100x Faster Bootstrapping in Fully Homomorphic Encryption through Memory-centric Optimization with GPUs (3), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (3), SHIP: A Shallow and Highly Parallelizable CKKS Bootstrapping Algorithm (3), Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS (3), Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-Sparse Keys (3), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (3), Approximate Homomorphic Encryption over the Conjugate-invariant Ring (3), ARION: Attention-optimized transformer inference on encrypted data (3), Security guidelines for implementing homomorphic encryption (2), Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption (2), Stay in Your Lane: Fast Arithmetic over Large Finite Rings with CKKS (2), A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (2), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (2), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (2), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (2), Federated Learning: An approach with Hybrid Homomorphic Encryption (2), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (2), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (2), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (2), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (2), Fully Homomorphic Encryption for Matrix Arithmetic (2), Improved Bootstrapping for Approximate Homomorphic Encryption (2), Bootstrapping for Approximate Homomorphic Encryption (2), Bootstrapping Bits with CKKS (2) …
Concrete (Zama) (51 papers)¶
Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (43), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (28), Towards Case-Optimized Hybrid Homomorphic Encryption (16), Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (14), Security guidelines for implementing homomorphic encryption (12), Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning (12), Pasta: A Case for Hybrid Homomorphic Encryption (9), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (9), A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (8), BLEACH: Cleaning Errors in Discrete Computations over CKKS (5), Fully Homomorphic Encryption for Machine Learning (4), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (3), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (3), Multiparty Computation from Somewhat Homomorphic Encryption (2), Stream ciphers: A Practical Solution for Efficient Homomorphic-Ciphertext Compression (2), The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption (2), Cryptanalysis of Symmetric Primitives over Rings and a Key Recovery Attack on Rubato (2), Revisiting Shamir Secret Sharing for Threshold Fully Homomorphic Encryption (2), Stay in Your Lane: Fast Arithmetic over Large Finite Rings with CKKS (2), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (2), BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption (2), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (2), OpenFHE: Open-Source Fully Homomorphic Encryption Library (2), BumbleBee: Secure Two-party Inference Framework for Large Transformers (2), TFHE Gets Real: An Efficient and Flexible Homomorphic Floating-Point Arithmetic (2), Bootstrapping Bits with CKKS (2), Homomorphic encryption standard (1), One server for the price of two: Simple and fast single-server private information retrieval (1), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (1), Privft: Private and fast text classification with homomorphic encryption (1), Probabilistic Encryption (1), Multi-Identity and Multi-Key Leveled FHE from Learning with Errors (1), Multiparty Computation with Low Communication, Computation and Interaction via Threshold FHE (1), Revisiting Module Lattice-based Homomorphic Encryption and Application to Secure-MPC (1), Efficient Homomorphic Integer Computer from CKKS (1), XBOOT: Free-XOR Gates for CKKS with Applications to Transciphering (1), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (1), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (1), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (1), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (1), Trace-Factored BigSwitch for Matrix-Friendly FHE (1), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (1), FINAL: Faster FHE Instantiated with NTRU and LWE (1), TFHE: Fast Fully Homomorphic Encryption over the Torus (1), PaCo: Bootstrapping for CKKS via Partial CoeffToSlot (1), General Functional Bootstrapping using CKKS (1), Securing Approximate Homomorphic Encryption Using Differential Privacy (1), Homomorphic Encryption for Arithmetic of Approximate Numbers (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1), STIP: Efficient and secure non-interactive transformer inference via compact packing (1), SoK: Private LLM Inference using Approximate Homomorphic Encryption (1)
Lattigo (45 papers)¶
ARION: Attention-optimized transformer inference on encrypted data (26), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (19), The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption (13), Stay in Your Lane: Fast Arithmetic over Large Finite Rings with CKKS (12), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (10), Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-Sparse Keys (8), SoK: Private LLM Inference using Approximate Homomorphic Encryption (8), Security guidelines for implementing homomorphic encryption (7), Multiparty Homomorphic Encryption from Ring-Learning-with-Errors (7), Efficient Bootstrapping in Fully Homomorphic Encryption for Matrix Arithmetic (6), Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS (5), SoK: Private transformer-based model inference (4), Transciphering Framework for Approximate Homomorphic Encryption (4), Accelerating HE Operations from Key Decomposition Technique (4), Securing Approximate Homomorphic Encryption Using Differential Privacy (4), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (4), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), Revisiting Shamir Secret Sharing for Threshold Fully Homomorphic Encryption (3), XBOOT: Free-XOR Gates for CKKS with Applications to Transciphering (3), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (3), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (3), Leveraging Discrete CKKS to Bootstrap in High Precision (3), Zephyr: GPU-Efficient Homomorphic Encryption for Privacy-Preserving Transformer Inference (3), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (2), Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version) (2), Bootstrapping for Approximate Homomorphic Encryption with Negligible Failure-Probability by Using Sparse-Secret Encapsulation (2), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (2), BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption (2), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (2), OpenFHE: Open-Source Fully Homomorphic Encryption Library (2), Revisiting Homomorphic Encryption Schemes for Finite Fields (2), Bootstrapping Bits with CKKS (2), On the Security of Homomorphic Encryption on Approximate Numbers (2), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (2), On the precision loss in approximate homomorphic encryption (1), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), Cryptanalysis of Symmetric Primitives over Rings and a Key Recovery Attack on Rubato (1), Revisiting Module Lattice-based Homomorphic Encryption and Application to Secure-MPC (1), Bootstrapping GBFV with CKKS (1), Relaxed Functional Bootstrapping: A New Perspective on BGV/BFV Bootstrapping (1), Efficient Homomorphic Integer Computer from CKKS (1), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (1), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (1), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (1), META-BTS: Bootstrapping Precision Beyond the Limit (1)
OpenFHE (45 papers)¶
OpenFHE: Open-Source Fully Homomorphic Encryption Library (100), Secure numerical simulations using fully homomorphic encryption (75), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (54), Security guidelines for implementing homomorphic encryption (25), SoK: Private LLM Inference using Approximate Homomorphic Encryption (21), Demystifying bootstrapping in fully homomorphic encryption (18), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (17), TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation (15), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (13), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (13), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (12), CKKS Bootstrapping in less than 10ms (10), Trace-Factored BigSwitch for Matrix-Friendly FHE (9), Private svm inference on encrypted data (8), Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS (8), High-Precision Functional Bootstrapping for CKKS from Fourier Extension (7), General Functional Bootstrapping using CKKS (7), Private pathological assessment via machine learning and homomorphic encryption (6), THEMIS: A Co-Designed System for Encrypted Transformer Inference (6), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (5), SoK: Private transformer-based model inference (4), High-Precision Homomorphic ALU over Arbitrary Moduli with O (1) Bootstrapping (4), FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext (4), The Power of Low Rank: Fast CKKS Functional Bootstrapping for High-Precision Lookup Tables (4), Stay in Your Lane: Fast Arithmetic over Large Finite Rings with CKKS (4), Fully Homomorphic Encryption for Matrix Arithmetic (4), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (3), Revisiting Shamir Secret Sharing for Threshold Fully Homomorphic Encryption (3), LFHE: Fully Homomorphic Encryption with Bootstrapping Key Size Less than a Megabyte (3), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (3), BLEACH: Cleaning Errors in Discrete Computations over CKKS (3), Bootstrapping Bits with CKKS (3), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (3), ENSI: Efficient non-interactive secure inference for large language models (3), TRICYCLE: Private transformer inference with tricyclic encodings (3), ARION: Attention-optimized transformer inference on encrypted data (3), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (2), Ajax: Fast Threshold Fully Homomorphic Encryption without Noise Flooding (2), Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption (2), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (2), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption (1), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (1), Leveraging Discrete CKKS to Bootstrap in High Precision (1)
PyTorch (44 papers)¶
CrypTen: Secure Multi-Party Computation Meets Machine Learning (30), ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs (25), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (18), Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage (17), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (16), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (13), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (12), SIGMA: Secure GPT Inference with Function Secret Sharing (9), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (6), fairseq: A fast, extensible toolkit for sequence modeling (5), Secure federated learning applied to medical imaging with fully homomorphic encryption (5), Theory, analysis, and best practices for sigmoid selfattention (4), SoK: Privacy-preserving computation techniques for deep learning (4), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (2), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (2), Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (2), TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption (2), Large language model inference acceleration: A comprehensive hardware perspective (1), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (1), Bitnet: Scaling 1-bit transformers for large language models (1), Llama: Open and efficient foundation language models (1), SoK: Private transformer-based model inference (1), Integrating large language models in financial investments and market analysis: A survey (1), Machine Learning Training on Encrypted Data with TFHE (1), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (1), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (1), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (1), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (1), FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (1), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (1), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (1), TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU (1), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (1), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (1), zkLLM: Zero Knowledge Proofs for Large Language Models (1), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (1), BumbleBee: Secure Two-party Inference Framework for Large Transformers (1), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (1), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (1), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (1), An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference (1), Converting transformers to polynomial form for secure inference over homomorphic encryption (1), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1)
Zama (30 papers)¶
Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (11), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (7), Security guidelines for implementing homomorphic encryption (6), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (6), Machine Learning Training on Encrypted Data with TFHE (5), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (2), Multi-key Fully Homomorphic Encryption with Non-Interactive Setup in the Plain Model (2), FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext (2), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (2), Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning (2), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (2), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (2), TFHE Gets Real: An Efficient and Flexible Homomorphic Floating-Point Arithmetic (2), Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks (2), BLEACH: Cleaning Errors in Discrete Computations over CKKS (2), On the precision loss in approximate homomorphic encryption (1), SoK: Private transformer-based model inference (1), Towards Case-Optimized Hybrid Homomorphic Encryption (1), Cryptanalysis of Symmetric Primitives over Rings and a Key Recovery Attack on Rubato (1), Ajax: Fast Threshold Fully Homomorphic Encryption without Noise Flooding (1), High-Precision Homomorphic ALU over Arbitrary Moduli with O (1) Bootstrapping (1), High-Precision Exact FHE Made Simple, General, and Fast (1), The Power of Low Rank: Fast CKKS Functional Bootstrapping for High-Precision Lookup Tables (1), Efficient Homomorphic Integer Computer from CKKS (1), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (1), A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (1), OpenFHE: Open-Source Fully Homomorphic Encryption Library (1), FINAL: Faster FHE Instantiated with NTRU and LWE (1), SHIP: A Shallow and Highly Parallelizable CKKS Bootstrapping Algorithm (1), General Functional Bootstrapping using CKKS (1)
EVA / CHET (29 papers)¶
EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (218), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (20), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (19), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (14), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (10), SoK: Privacy-preserving computation techniques for deep learning (9), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (9), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (8), Private and reliable neural network inference (5), Security guidelines for implementing homomorphic encryption (5), SoK: Private transformer-based model inference (4), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (4), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (3), Secure human action recognition by encrypted neural network inference (3), Delphi: A Cryptographic Inference Service for Neural Networks (3), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (3), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (2), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (2), On the Security of Homomorphic Encryption on Approximate Numbers (2), Pasta: A Case for Hybrid Homomorphic Encryption (1), COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025 (1), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (1), Fully Homomorphically Encrypted Deep Learning as a Service (1), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (1), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (1), OpenFHE: Open-Source Fully Homomorphic Encryption Library (1), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (1), CrypTFlow2: Practical 2-Party Secure Inference (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1)
PALISADE (29 papers)¶
On the Security of Homomorphic Encryption on Approximate Numbers (15), Approximate Homomorphic Encryption with Reduced Approximation Error (15), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (11), Revisiting Homomorphic Encryption Schemes for Finite Fields (11), Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption (10), TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation (10), OpenFHE: Open-Source Fully Homomorphic Encryption Library (10), Securing Approximate Homomorphic Encryption Using Differential Privacy (10), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (9), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (8), Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption (4), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (4), Homomorphic encryption standard (3), Large-Plaintext Functional Bootstrapping in FHE with Small Bootstrapping Keys (3), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (3), High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function (3), A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (2), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (2), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (2), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (2), Multiparty Homomorphic Encryption from Ring-Learning-with-Errors (2), On the precision loss in approximate homomorphic encryption (1), The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption (1), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (1), Fully Homomorphically Encrypted Deep Learning as a Service (1), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (1), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (1), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (1), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (1)
ABY / ABY3 (27 papers)¶
SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (23), MP-SPDZ: A Versatile Framework for Multi-Party Computation (22), ABY3: A Mixed Protocol Framework for Machine Learning (16), SoK: Privacy-preserving computation techniques for deep learning (15), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (9), SoK: Private transformer-based model inference (6), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (5), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (4), CrypTen: Secure Multi-Party Computation Meets Machine Learning (4), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (3), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (2), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (2), BumbleBee: Secure Two-party Inference Framework for Large Transformers (2), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2), CrypTFlow2: Practical 2-Party Secure Inference (2), Delphi: A Cryptographic Inference Service for Neural Networks (2), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (2), Secure outsourced matrix computation and application to neural networks (1), Cryptanalysis of Symmetric Primitives over Rings and a Key Recovery Attack on Rubato (1), COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025 (1), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (1), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (1), Non-interactive Fully Encrypted Machine Learning Protocol for Inference (1), MPC-Minimized Secure LLM Inference (1), SIGMA: Secure GPT Inference with Function Secret Sharing (1), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (1), BLEACH: Cleaning Errors in Discrete Computations over CKKS (1)
EzPC / CrypTFlow (27 papers)¶
CrypTFlow2: Practical 2-Party Secure Inference (24), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (22), SoK: Private transformer-based model inference (13), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (12), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (10), SoK: Privacy-preserving computation techniques for deep learning (9), CrypTen: Secure Multi-Party Computation Meets Machine Learning (6), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (5), BumbleBee: Secure Two-party Inference Framework for Large Transformers (5), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (5), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (4), SIGMA: Secure GPT Inference with Function Secret Sharing (4), CipherGPT: Secure Two-Party GPT Inference (4), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (3), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (2), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (2), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (2), Iron: Private Inference on Transformers (2), Delphi: A Cryptographic Inference Service for Neural Networks (2), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (2), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (1), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (1), Non-interactive Fully Encrypted Machine Learning Protocol for Inference (1), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (1), MP-SPDZ: A Versatile Framework for Multi-Party Computation (1), MPC-Minimized Secure LLM Inference (1), BLEACH: Cleaning Errors in Discrete Computations over CKKS (1)
TensorFlow (27 papers)¶
ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs (13), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (12), CrypTFlow2: Practical 2-Party Secure Inference (8), CrypTen: Secure Multi-Party Computation Meets Machine Learning (5), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (3), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (3), Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (3), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (2), Iron: Private Inference on Transformers (2), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (2), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (1), SoK: Private transformer-based model inference (1), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (1), SoK: Privacy-preserving computation techniques for deep learning (1), Integrating large language models in financial investments and market analysis: A survey (1), Fully Homomorphic Encryption for Machine Learning (1), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (1), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (1), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (1), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (1), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (1), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (1), PrivateLoRA for Efficient Privacy Preserving LLM (1), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (1), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (1), SIGMA: Secure GPT Inference with Function Secret Sharing (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1)
MP-SPDZ (22 papers)¶
MP-SPDZ: A Versatile Framework for Multi-Party Computation (130), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (18), Iron: Private Inference on Transformers (10), Multiparty Homomorphic Encryption from Ring-Learning-with-Errors (8), SoK: Privacy-preserving computation techniques for deep learning (6), SoK: Private transformer-based model inference (4), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (3), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (2), ABY3: A Mixed Protocol Framework for Machine Learning (2), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (2), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (2), Ajax: Fast Threshold Fully Homomorphic Encryption without Noise Flooding (1), Revisiting Module Lattice-based Homomorphic Encryption and Application to Secure-MPC (1), Bootstrapping GBFV with CKKS (1), Faster Logical Operations from Discrete CKKS (1), SIGMA: Secure GPT Inference with Function Secret Sharing (1), CrypTFlow2: Practical 2-Party Secure Inference (1), Delphi: A Cryptographic Inference Service for Neural Networks (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1)
nGraph-HE (22 papers)¶
Secure human action recognition by encrypted neural network inference (19), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (10), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (6), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (6), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (4), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (3), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (3), SoK: Privacy-preserving computation techniques for deep learning (2), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (2), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (2), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (2), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (2), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2), CrypTFlow2: Practical 2-Party Secure Inference (2), Better Bootstrapping for Approximate Homomorphic Encryption (2), High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function (2), BLEACH: Cleaning Errors in Discrete Computations over CKKS (2), SoK: Private transformer-based model inference (1), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (1), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (1), On the Security of Homomorphic Encryption on Approximate Numbers (1), THEMIS: A Co-Designed System for Encrypted Transformer Inference (1)
HEaaN (library) (20 papers)¶
SHIP: A Shallow and Highly Parallelizable CKKS Bootstrapping Algorithm (24), TRICYCLE: Private transformer inference with tricyclic encodings (18), Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused (9), Bootstrapping Bits with CKKS (9), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (6), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (6), Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS (6), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (5), Fast and Accurate Homomorphic Softmax Evaluation (5), Encryption-friendly LLM architecture (5), BLEACH: Cleaning Errors in Discrete Computations over CKKS (4), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (3), Leveraging Discrete CKKS to Bootstrap in High Precision (3), SoK: Private LLM Inference using Approximate Homomorphic Encryption (3), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (2), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), SoK: Private transformer-based model inference (2), Security guidelines for implementing homomorphic encryption (1), META-BTS: Bootstrapping Precision Beyond the Limit (1), Converting transformers to polynomial form for secure inference over homomorphic encryption (1)
Phantom (20 papers)¶
SoK: Private LLM Inference using Approximate Homomorphic Encryption (17), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (14), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (8), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (6), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (6), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), ARION: Attention-optimized transformer inference on encrypted data (3), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (3), HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge (2), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (2), ENSI: Efficient non-interactive secure inference for large language models (2), STIP: Efficient and secure non-interactive transformer inference via compact packing (2), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (2), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (2), Secure numerical simulations using fully homomorphic encryption (1), Security guidelines for implementing homomorphic encryption (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1), Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference (1), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1), A scalable multi-GPU framework for encrypted large-model inference (1)
CrypTen (19 papers)¶
SIGMA: Secure GPT Inference with Function Secret Sharing (54), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (24), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (22), SoK: Private transformer-based model inference (17), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (17), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (11), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (7), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (4), CrypTen: Secure Multi-Party Computation Meets Machine Learning (4), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (3), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (2), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (2), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (2), PUMA: Secure Inference of LLaMA-7B in Five Minutes (2), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (2), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (1), COMPARISON OF FULLY HOMOMORPHIC ENCRYPTION AND GARBLED CIRCUITS APPROACHES IN PRIVACY-PRESERVING MACHINE LEARNING Kalyan Cheerla Thesis Prepared for the Degree of MASTER OF SCIENCE UNIVERSITY OF NORTH TEXAS July 2025 (1), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (1), MPC-Minimized Secure LLM Inference (1)
HuggingFace (16 papers)¶
SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (13), Large language model inference acceleration: A comprehensive hardware perspective (4), SIGMA: Secure GPT Inference with Function Secret Sharing (3), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (3), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (2), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (2), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (2), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (2), SoK: Private transformer-based model inference (1), Beyond memorization: Violating privacy via inference with large language models (1), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (1), Nimbus: Secure and Efficient Two-Party Inference for Transformers (1), BumbleBee: Secure Two-party Inference Framework for Large Transformers (1), PUMA: Secure Inference of LLaMA-7B in Five Minutes (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (1)
TenSEAL (15 papers)¶
HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (32), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (18), TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption (12), Secure federated learning applied to medical imaging with fully homomorphic encryption (10), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (7), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (3), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (3), Private and reliable neural network inference (2), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (2), FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (2), Federated Learning: An approach with Hybrid Homomorphic Encryption (2), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (1), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (1)
TFHE-rs (15 papers)¶
Security guidelines for implementing homomorphic encryption (13), Efficient Homomorphic Integer Computer from CKKS (10), FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext (8), General Functional Bootstrapping using CKKS (7), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (6), TFHE Gets Real: An Efficient and Flexible Homomorphic Floating-Point Arithmetic (5), SoK: Private transformer-based model inference (4), High-Precision Homomorphic ALU over Arbitrary Moduli with O (1) Bootstrapping (4), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (3), SWIFT: Shallow and SIMD-Aware CKKS Functional Bootstrapping for Low-Latency (3), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (2), Ajax: Fast Threshold Fully Homomorphic Encryption without Noise Flooding (2), High-Precision Exact FHE Made Simple, General, and Fast (2), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (2), SHIP: A Shallow and Highly Parallelizable CKKS Bootstrapping Algorithm (2)
Orion (14 papers)¶
Orion: A Fully Homomorphic Encryption Framework for Deep Learning (90), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (16), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (5), SoK: Private transformer-based model inference (3), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (2), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (2), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (2), SoK: Private LLM Inference using Approximate Homomorphic Encryption (2), FHE for SIMD Arithmetic Logic Units with Amortized O(1) Bootstrapping per Ciphertext (1), zkLLM: Zero Knowledge Proofs for Large Language Models (1), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (1), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (1), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (1), A scalable multi-GPU framework for encrypted large-model inference (1)
Liberate.FHE (12 papers)¶
EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (16), TRICYCLE: Private transformer inference with tricyclic encodings (6), SoK: Private LLM Inference using Approximate Homomorphic Encryption (6), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (4), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (3), ARION: Attention-optimized transformer inference on encrypted data (3), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), Security guidelines for implementing homomorphic encryption (1), SoK: Private transformer-based model inference (1), Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption (1), A scalable multi-GPU framework for encrypted large-model inference (1), THOR: Secure transformer inference with homomorphic encryption (1)
SecretFlow-SPU (11 papers)¶
SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (199), SoK: Private transformer-based model inference (10), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (8), BumbleBee: Secure Two-party Inference Framework for Large Transformers (8), Nimbus: Secure and Efficient Two-Party Inference for Transformers (7), PUMA: Secure Inference of LLaMA-7B in Five Minutes (7), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (3), Secure transformer inference made non-interactive (3), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (2), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (2)
Cheddar (10 papers)¶
Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (71), Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference (13), A scalable multi-GPU framework for encrypted large-model inference (8), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (6), Zephyr: GPU-Efficient Homomorphic Encryption for Privacy-Preserving Transformer Inference (6), HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge (2), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (2), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (2), Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference (2), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1)
HELayers (8 papers)¶
HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (16), BLEACH: Cleaning Errors in Discrete Computations over CKKS (6), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (4), ARION: Attention-optimized transformer inference on encrypted data (4), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (3), SoK: Private LLM Inference using Approximate Homomorphic Encryption (3), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (2), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (1)
ONNX (8 papers)¶
HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (29), Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (7), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (6), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (3), Machine Learning Training on Encrypted Data with TFHE (2), CrypTen: Secure Multi-Party Computation Meets Machine Learning (2), Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks (2), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (1)
HEonGPU (6 papers)¶
HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (102), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (4), SoK: Private transformer-based model inference (2), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (2), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (1), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1)
Pyfhel (6 papers)¶
BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (11), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (4), SoK: Private transformer-based model inference (4), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (4), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), SpyKing—Privacy-preserving framework for Spiking Neural Networks (1)
Concrete ML (5 papers)¶
Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (26), Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (11), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (8), A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (8), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (2)
cuFHE / nuFHE (5 papers)¶
Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (4), Homomorphic encryption standard (3), Over 100x Faster Bootstrapping in Fully Homomorphic Encryption through Memory-centric Optimization with GPUs (3), Demystifying bootstrapping in fully homomorphic encryption (1), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (1)
cuHE (5 papers)¶
Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (8), Homomorphic encryption standard (3), A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (2), Private and reliable neural network inference (1), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (1)
Fhelipe (5 papers)¶
Orion: A Fully Homomorphic Encryption Framework for Deep Learning (14), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (6), SoK: Private transformer-based model inference (2), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (2), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1)
FIDESlib (5 papers)¶
FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (75), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (13), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (5), SoK: Private LLM Inference using Approximate Homomorphic Encryption (2), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1)
HEIR (4 papers)¶
OpenFHE: Open-Source Fully Homomorphic Encryption Library (4), SoK: Private transformer-based model inference (2), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1), A scalable multi-GPU framework for encrypted large-model inference (1)