Skip to content

Browse by model

Declared in extracted details

Values reported by the structured extraction (field models).

Mentions in full text

Papers ordered by how often the term occurs (count in brackets). Only papers with a local PDF are counted.

CNN (108 papers)

Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (87), Secure human action recognition by encrypted neural network inference (50), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (49), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (46), On Fully Homomorphic Encryption for Privacy-Preserving Deep Learning (34), Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (34), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (30), Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning (26), Fully Homomorphically Encrypted Deep Learning as a Service (24), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (20), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (19), A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (16), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (15), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (13), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (13), Secure outsourced matrix computation and application to neural networks (12), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (12), Homomorphic Encryption for Machine Learning and Artificial Intelligence Applications (12), InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model (12), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (12), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (11), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (10), Secure transformer inference made non-interactive (10), zkLLM: Zero Knowledge Proofs for Large Language Models (9), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (8), Fully Homomorphic Encryption with Applications to Privacy-Preserving Machine Learning (7), An Efficient and Privacy-Preserving Federated Learning Approach Based on Homomorphic Encryption (7), Private pathological assessment via machine learning and homomorphic encryption (7), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (7), Integrating large language models in financial investments and market analysis: A survey (6), Towards Case-Optimized Hybrid Homomorphic Encryption (6), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (6), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (6), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (6), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (6), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (6), SIGMA: Secure GPT Inference with Function Secret Sharing (6), Converting transformers to polynomial form for secure inference over homomorphic encryption (6), fairseq: A fast, extensible toolkit for sequence modeling (5), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (5), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (5), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (5), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (5), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (5), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (5), Iron: Private Inference on Transformers (5), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (5), A comprehensive survey on secure outsourced computation and its applications (4), SoK: Privacy-preserving computation techniques for deep learning (4), Private svm inference on encrypted data (4), ABY3: A Mixed Protocol Framework for Machine Learning (4), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (4), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (4), FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (4), Federated Learning: An approach with Hybrid Homomorphic Encryption (4), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (4), TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption (4), BumbleBee: Secure Two-party Inference Framework for Large Transformers (4), High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function (4), Private and reliable neural network inference (3) …

Logistic regression (74 papers)

Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (81), Efficient Homomorphic Evaluation on Large Intervals (38), Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption (33), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (26), ABY3: A Mixed Protocol Framework for Machine Learning (24), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (21), Stealing machine learning models via prediction APIs (20), SQuAD: 100,000+ questions for machine comprehension of text (16), Machine Learning Training on Encrypted Data with TFHE (14), A comprehensive survey on secure outsourced computation and its applications (11), Efficiency Optimization Techniques in Privacy-Preserving Federated Learning With Homomorphic Encryption: A Brief Survey (11), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (10), BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption (9), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (8), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (7), TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation (7), Over 100x Faster Bootstrapping in Fully Homomorphic Encryption through Memory-centric Optimization with GPUs (6), Better Bootstrapping for Approximate Homomorphic Encryption (6), Improved Bootstrapping for Approximate Homomorphic Encryption (6), A Full RNS Variant of Approximate Homomorphic Encryption (5), Secure numerical simulations using fully homomorphic encryption (4), A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (4), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (4), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (4), On the Security of Homomorphic Encryption on Approximate Numbers (4), Homomorphic Encryption for Arithmetic of Approximate Numbers (4), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (3), Private svm inference on encrypted data (3), ModHE: Modular Homomorphic Encryption Using Module Lattices: Potentials and Limitations (3), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (3), Private pathological assessment via machine learning and homomorphic encryption (3), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (3), TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU (3), MP-SPDZ: A Versatile Framework for Multi-Party Computation (3), Bootstrapping for Approximate Homomorphic Encryption (3), Approximate Homomorphic Encryption with Reduced Approximation Error (3), Approximate Homomorphic Encryption over the Conjugate-invariant Ring (3), Secure outsourced matrix computation and application to neural networks (2), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (2), SoK: Privacy-preserving computation techniques for deep learning (2), Demystifying bootstrapping in fully homomorphic encryption (2), Privft: Private and fast text classification with homomorphic encryption (2), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (2), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (2), FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs (2), High-Precision Arithmetic in Homomorphic Encryption (2), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (2), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (2), On the precision loss in approximate homomorphic encryption (1), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (1), Integrating large language models in financial investments and market analysis: A survey (1), The HHE Land: Exploring the Landscape of 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), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (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), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (1), Secure human action recognition by encrypted neural network inference (1), Non-interactive Fully Encrypted Machine Learning Protocol for Inference (1), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (1) …

Transformer (73 papers)

MPCFormer: Fast, Performant and Private Transformer Inference with MPC (71), Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference (53), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (52), Bitnet: Scaling 1-bit transformers for large language models (49), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (49), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (42), Nimbus: Secure and Efficient Two-Party Inference for Transformers (40), PUMA: Secure Inference of LLaMA-7B in Five Minutes (35), Iron: Private Inference on Transformers (35), SoK: Private transformer-based model inference (34), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (34), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (31), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (29), THEMIS: A Co-Designed System for Encrypted Transformer Inference (28), ARION: Attention-optimized transformer inference on encrypted data (27), Large language model inference acceleration: A comprehensive hardware perspective (26), Attention is all you need (26), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (26), TRICYCLE: Private transformer inference with tricyclic encodings (26), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (25), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (24), Privacypreserving llm inference in practice: A comparative survey of techniques, trade-offs, and deployability (23), BERT: Pre-training of deep bidirectional transformers for language understanding (22), BumbleBee: Secure Two-party Inference Framework for Large Transformers (22), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (21), An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference (19), Theory, analysis, and best practices for sigmoid selfattention (16), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (16), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (15), THOR: Secure transformer inference with homomorphic encryption (15), SoK: Private LLM Inference using Approximate Homomorphic Encryption (15), Improving language understanding by generative pretraining (14), SIGMA: Secure GPT Inference with Function Secret Sharing (14), Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B (v1: Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B) (13), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (12), Converting transformers to polynomial form for secure inference over homomorphic encryption (12), Large language models in medicine (11), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (10), Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption (10), fairseq: A fast, extensible toolkit for sequence modeling (9), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (9), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (9), ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs (8), MPC-Minimized Secure LLM Inference (7), Zephyr: GPU-Efficient Homomorphic Encryption for Privacy-Preserving Transformer Inference (7), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (7), zkLLM: Zero Knowledge Proofs for Large Language Models (6), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (5), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (5), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (5), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (5), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (5), Integrating large language models in financial investments and market analysis: A survey (4), 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 (4), STIP: Efficient and secure non-interactive transformer inference via compact packing (4), Secure transformer inference made non-interactive (4), Private svm inference on encrypted data (3), PrivateLoRA for Efficient Privacy Preserving LLM (3), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (3), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (3) …

GPT (63 papers)

GPT-4 System Card (253), Large language models in medicine (79), Integrating large language models in financial investments and market analysis: A survey (62), SIGMA: Secure GPT Inference with Function Secret Sharing (52), Large language model inference acceleration: A comprehensive hardware perspective (51), Beyond memorization: Violating privacy via inference with large language models (50), InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model (49), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (45), CipherGPT: Secure Two-Party GPT Inference (44), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (43), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (42), PUMA: Secure Inference of LLaMA-7B in Five Minutes (41), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (39), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (35), Llama: Open and efficient foundation language models (31), BERT: Pre-training of deep bidirectional transformers for language understanding (28), SoK: Private transformer-based model inference (28), SoK: Private LLM Inference using Approximate Homomorphic Encryption (21), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (20), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (20), Trace-Factored BigSwitch for Matrix-Friendly FHE (19), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (18), BumbleBee: Secure Two-party Inference Framework for Large Transformers (16), HellaSwag: Can a machine really finish your sentence? (14), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (13), STIP: Efficient and secure non-interactive transformer inference via compact packing (12), Privacypreserving llm inference in practice: A comparative survey of techniques, trade-offs, and deployability (11), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (11), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (9), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (8), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (7), Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage (6), (a)i am not a lawyer, but...: Engaging legal experts towards responsible llm policies for legal advice (6), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (5), zkLLM: Zero Knowledge Proofs for Large Language Models (5), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (5), Secure transformer inference made non-interactive (5), Encryption-friendly LLM architecture (5), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (4), ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs (3), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (3), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (3), Bitnet: Scaling 1-bit transformers for large language models (2), 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 (2), MPC-Minimized Secure LLM Inference (2), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (2), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (2), Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused (2), THEMIS: A Co-Designed System for Encrypted Transformer Inference (2), ARION: Attention-optimized transformer inference on encrypted data (2), Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B (v1: Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B) (2), THOR: Secure transformer inference with homomorphic encryption (2), Theory, analysis, and best practices for sigmoid selfattention (1), Bootstrapping GBFV with CKKS (1), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (1), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (1), PrivateLoRA for Efficient Privacy Preserving LLM (1), Nimbus: Secure and Efficient Two-Party Inference for Transformers (1), Iron: Private Inference on Transformers (1), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (1) …

BERT (58 papers)

SoK: Private transformer-based model inference (96), ARION: Attention-optimized transformer inference on encrypted data (84), BERT: Pre-training of deep bidirectional transformers for language understanding (80), HellaSwag: Can a machine really finish your sentence? (62), SoK: Private LLM Inference using Approximate Homomorphic Encryption (60), ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs (59), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (56), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (55), TRICYCLE: Private transformer inference with tricyclic encodings (51), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (45), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (42), SIGMA: Secure GPT Inference with Function Secret Sharing (42), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (39), A scalable multi-GPU framework for encrypted large-model inference (31), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (27), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (27), Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference (24), Iron: Private Inference on Transformers (23), Secure transformer inference made non-interactive (21), BumbleBee: Secure Two-party Inference Framework for Large Transformers (20), STIP: Efficient and secure non-interactive transformer inference via compact packing (20), Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption (19), Encryption-friendly LLM architecture (19), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (15), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (14), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (14), THOR: Secure transformer inference with homomorphic encryption (14), InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model (13), THEMIS: A Co-Designed System for Encrypted Transformer Inference (11), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (10), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (10), Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference (9), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (7), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (7), Large language model inference acceleration: A comprehensive hardware perspective (6), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (6), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (6), An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference (6), Converting transformers to polynomial form for secure inference over homomorphic encryption (6), Privacypreserving llm inference in practice: A comparative survey of techniques, trade-offs, and deployability (4), Privft: Private and fast text classification with homomorphic encryption (4), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (4), Bitnet: Scaling 1-bit transformers for large language models (3), Large language models in medicine (3), MPC-Minimized Secure LLM Inference (3), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (3), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (3), Zephyr: GPU-Efficient Homomorphic Encryption for Privacy-Preserving Transformer Inference (3), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (3), Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused (2), Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage (1), Llama: Open and efficient foundation language models (1), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (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), Nimbus: Secure and Efficient Two-Party Inference for Transformers (1), CipherGPT: Secure Two-Party GPT Inference (1), Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B (v1: Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B) (1)

LLaMA (56 papers)

Llama: Open and efficient foundation language models (71), PrivateLoRA for Efficient Privacy Preserving LLM (66), An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference (52), SoK: Private LLM Inference using Approximate Homomorphic Encryption (47), Large language model inference acceleration: A comprehensive hardware perspective (33), Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B (v1: Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B) (31), PUMA: Secure Inference of LLaMA-7B in Five Minutes (28), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (27), Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study (25), Integrating large language models in financial investments and market analysis: A survey (22), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (20), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (19), SoK: Private transformer-based model inference (17), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (16), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (13), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (12), ARION: Attention-optimized transformer inference on encrypted data (12), Beyond memorization: Violating privacy via inference with large language models (11), ENSI: Efficient non-interactive secure inference for large language models (11), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (10), BumbleBee: Secure Two-party Inference Framework for Large Transformers (10), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (9), Trace-Factored BigSwitch for Matrix-Friendly FHE (8), Secure transformer inference made non-interactive (8), TRICYCLE: Private transformer inference with tricyclic encodings (8), Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage (7), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (7), Privacypreserving llm inference in practice: A comparative survey of techniques, trade-offs, and deployability (7), Large language models in medicine (7), zkLLM: Zero Knowledge Proofs for Large Language Models (7), MPC-Minimized Secure LLM Inference (6), Fast and Accurate Homomorphic Softmax Evaluation (6), Encryption-friendly LLM architecture (6), SIGMA: Secure GPT Inference with Function Secret Sharing (5), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (4), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (3), Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused (3), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (3), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (3), Theory, analysis, and best practices for sigmoid selfattention (2), Bitnet: Scaling 1-bit transformers for large language models (2), InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model (2), Nimbus: Secure and Efficient Two-Party Inference for Transformers (2), STIP: Efficient and secure non-interactive transformer inference via compact packing (2), THOR: Secure transformer inference with homomorphic encryption (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), (a)i am not a lawyer, but...: Engaging legal experts towards responsible llm policies for legal advice (1), SWIFT: Shallow and SIMD-Aware CKKS Functional Bootstrapping for Low-Latency (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), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (1), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (1), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1), Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference (1), Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference (1), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (1)

RNN / LSTM (49 papers)

Pointer sentinel mixture models (136), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (36), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (28), Recursive deep models for semantic compositionality over a sentiment treebank (27), The LAMBADA dataset: Word prediction requiring a broad discourse context (16), BERT: Pre-training of deep bidirectional transformers for language understanding (13), Attention is all you need (11), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (10), HellaSwag: Can a machine really finish your sentence? (9), TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU (7), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (7), Improving language understanding by generative pretraining (6), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (6), Large language model inference acceleration: A comprehensive hardware perspective (5), Privft: Private and fast text classification with homomorphic encryption (5), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (4), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (4), Theory, analysis, and best practices for sigmoid selfattention (3), Private pathological assessment via machine learning and homomorphic encryption (3), THOR: Secure transformer inference with homomorphic encryption (3), fairseq: A fast, extensible toolkit for sequence modeling (2), A comprehensive survey on secure outsourced computation and its applications (2), Secure Federated Learning With Fully Homomorphic Encryption for IoT Communications (2), Iron: Private Inference on Transformers (2), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (2), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (1), SQuAD: 100,000+ questions for machine comprehension of text (1), Llama: Open and efficient foundation language models (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), Integrating large language models in financial investments and market analysis: A survey (1), Secure human action recognition by encrypted neural network inference (1), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (1), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (1), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (1), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (1), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (1), MPC-Minimized Secure LLM Inference (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), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (1), SIGMA: Secure GPT Inference with Function Secret Sharing (1), CipherGPT: Secure Two-Party GPT Inference (1), PUMA: Secure Inference of LLaMA-7B in Five Minutes (1), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (1), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (1), Secure transformer inference made non-interactive (1), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (1)

ResNet (35 papers)

Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (62), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (48), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (45), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (32), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (30), CrypTFlow2: Practical 2-Party Secure Inference (25), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (24), Delphi: A Cryptographic Inference Service for Neural Networks (20), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (19), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (19), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (18), Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (18), A scalable multi-GPU framework for encrypted large-model inference (18), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (17), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (16), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (15), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (9), CrypTen: Secure Multi-Party Computation Meets Machine Learning (9), TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU (8), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (4), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (4), Converting transformers to polynomial form for secure inference over homomorphic encryption (3), 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), 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), Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption (1), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (1), Secure human action recognition by encrypted neural network inference (1), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (1), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (1), HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge (1), Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (1), FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (1), MP-SPDZ: A Versatile Framework for Multi-Party Computation (1)

Decision tree (32 papers)

Private machine learning classification based on fully homomorphic encryption (28), Stealing machine learning models via prediction APIs (27), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (21), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (18), Application of Machine Learning-NLP Approach with Fully Homomorphic Encryption Techniques in Medical PII Data (11), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (7), A comprehensive survey on secure outsourced computation and its applications (4), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (3), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (3), TFHE: Fast Fully Homomorphic Encryption over the Torus (3), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (2), Multi-key Fully Homomorphic Encryption with Non-Interactive Setup in the Plain Model (2), A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (2), BLEACH: Cleaning Errors in Discrete Computations over CKKS (2), Demystifying bootstrapping in fully homomorphic encryption (1), Breaking the Circuit Size Barrier for Secure Computation Under DDH (1), ABY3: A Mixed Protocol Framework for Machine Learning (1), The HHE Land: Exploring the Landscape of Hybrid Homomorphic Encryption (1), Large-Plaintext Functional Bootstrapping in FHE with Small Bootstrapping Keys (1), Fully Homomorphic Encryption for Machine Learning (1), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (1), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (1), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (1), Efficiency Optimization Techniques in Privacy-Preserving Federated Learning With Homomorphic Encryption: A Brief Survey (1), An Efficient Architecture for Edge AI Federated Learning With Homomorphic Encryption (1), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (1), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (1), zkLLM: Zero Knowledge Proofs for Large Language Models (1), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (1), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (1), CipherGPT: Secure Two-Party GPT Inference (1), Delphi: A Cryptographic Inference Service for Neural Networks (1)

SVM (28 papers)

Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (120), Private svm inference on encrypted data (114), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (109), Private pathological assessment via machine learning and homomorphic encryption (105), Stealing machine learning models via prediction APIs (35), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (18), A comprehensive survey on secure outsourced computation and its applications (13), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (9), Automatically constructing a corpus of sentential paraphrases (5), ABY3: A Mixed Protocol Framework for Machine Learning (5), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (5), Recursive deep models for semantic compositionality over a sentiment treebank (4), Secure outsourced matrix computation and application to neural networks (2), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (2), zkLLM: Zero Knowledge Proofs for Large Language Models (2), Delphi: A Cryptographic Inference Service for Neural Networks (2), Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version) (1), Transciphering Framework for Approximate Homomorphic Encryption (1), Fully Homomorphic Encryption for Machine Learning (1), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (1), Private machine learning classification based on fully homomorphic encryption (1), Secure federated learning applied to medical imaging with fully homomorphic encryption (1), Federated Learning with Quantum Computing and Fully Homomorphic Encryption: A Novel Computing Paradigm Shift in Privacy-Preserving ML (1), A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (1), CrypTen: Secure Multi-Party Computation Meets Machine Learning (1), CipherGPT: Secure Two-Party GPT Inference (1), Securing Approximate Homomorphic Encryption Using Differential Privacy (1), SoK: Private LLM Inference using Approximate Homomorphic Encryption (1)

AlexNet (23 papers)

HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (40), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (22), Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (15), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (7), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (6), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (3), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (3), A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (2), Private and reliable neural network inference (1), Secure outsourced matrix computation and application to neural networks (1), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (1), Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning (1), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (1), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (1), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (1), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (1), Secure federated learning applied to medical imaging with fully homomorphic encryption (1), Private pathological assessment via machine learning and homomorphic encryption (1), CrypTen: Secure Multi-Party Computation Meets Machine Learning (1), CrypTFlow2: Practical 2-Party Secure Inference (1), Converting transformers to polynomial form for secure inference over homomorphic encryption (1), ENSI: Efficient non-interactive secure inference for large language models (1)

MLP (23 papers)

Stealing machine learning models via prediction APIs (16), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (16), Machine Learning Training on Encrypted Data with TFHE (13), Theory, analysis, and best practices for sigmoid selfattention (10), Converting transformers to polynomial form for secure inference over homomorphic encryption (5), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (4), Fully Homomorphic Encryption for Machine Learning (4), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (4), SWIFT: Shallow and SIMD-Aware CKKS Functional Bootstrapping for Low-Latency (3), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (3), zkLLM: Zero Knowledge Proofs for Large Language Models (3), CrypTen: Secure Multi-Party Computation Meets Machine Learning (3), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (3), HellaSwag: Can a machine really finish your sentence? (2), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (2), Pointer sentinel mixture models (1), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (1), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (1), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (1), Secure Federated Learning With Fully Homomorphic Encryption for IoT Communications (1), PrivateLoRA for Efficient Privacy Preserving LLM (1), An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference (1)

ViT (21 papers)

ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (30), Theory, analysis, and best practices for sigmoid selfattention (23), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (23), SoK: Private transformer-based model inference (22), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (20), Converting transformers to polynomial form for secure inference over homomorphic encryption (19), BumbleBee: Secure Two-party Inference Framework for Large Transformers (18), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (13), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (10), CrypTen: Secure Multi-Party Computation Meets Machine Learning (7), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (5), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (3), ARION: Attention-optimized transformer inference on encrypted data (3), Large language models in medicine (2), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (2), Iron: Private Inference on Transformers (2), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (1), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (1), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (1), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (1)

Linear regression (16 papers)

ABY3: A Mixed Protocol Framework for Machine Learning (24), A comprehensive survey on secure outsourced computation and its applications (10), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (5), SoK: Privacy-preserving computation techniques for deep learning (3), Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (3), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (2), Private pathological assessment via machine learning and homomorphic encryption (2), Delphi: A Cryptographic Inference Service for Neural Networks (2), Stealing machine learning models via prediction APIs (1), HellaSwag: Can a machine really finish your sentence? (1), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), (a)i am not a lawyer, but...: Engaging legal experts towards responsible llm policies for legal advice (1), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (1), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (1), CipherGPT: Secure Two-Party GPT Inference (1), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (1)

LeNet (15 papers)

Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (31), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (24), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (14), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (14), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (12), SpyKing—Privacy-preserving framework for Spiking Neural Networks (7), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (5), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (4), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (3), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (1), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (1), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (1), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (1), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (1), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (1)

VGG (14 papers)

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (26), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (16), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (10), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (4), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (4), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (3), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (1), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (1), zkLLM: Zero Knowledge Proofs for Large Language Models (1), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (1), CrypTen: Secure Multi-Party Computation Meets Machine Learning (1), SIGMA: Secure GPT Inference with Function Secret Sharing (1), CipherGPT: Secure Two-Party GPT Inference (1)

MobileNet (13 papers)

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (27), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (15), PPFLHE: A privacy-preserving federated learning scheme with homomorphic encryption for healthcare data (9), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (9), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (5), Secure federated learning applied to medical imaging with fully homomorphic encryption (5), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (4), A scalable multi-GPU framework for encrypted large-model inference (2), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (1), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (1), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (1), TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption (1), MP-SPDZ: A Versatile Framework for Multi-Party Computation (1)

LoRA (12 papers)

Encryption-friendly LLM architecture (83), Practical secure inference algorithm for a fine-tuned large language model based on fully homomorphic encryption (34), MPC-Minimized Secure LLM Inference (32), PrivateLoRA for Efficient Privacy Preserving LLM (29), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (12), Integrating large language models in financial investments and market analysis: A survey (10), SoK: Private transformer-based model inference (3), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (3), SoK: Private LLM Inference using Approximate Homomorphic Encryption (3), Large language model inference acceleration: A comprehensive hardware perspective (2), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (2), A scalable multi-GPU framework for encrypted large-model inference (1)

Autoencoder (11 papers)

Private pathological assessment via machine learning and homomorphic encryption (8), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (4), Theory, analysis, and best practices for sigmoid selfattention (2), Recursive deep models for semantic compositionality over a sentiment treebank (2), Improving language understanding by generative pretraining (2), BERT: Pre-training of deep bidirectional transformers for language understanding (2), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (1), Fully Homomorphically Encrypted Deep Learning as a Service (1), Efficiency Optimization Techniques in Privacy-Preserving Federated Learning With Homomorphic Encryption: A Brief Survey (1), Secure Federated Learning With Fully Homomorphic Encryption for IoT Communications (1), PUMA: Secure Inference of LLaMA-7B in Five Minutes (1)

k-NN (11 papers)

A comprehensive survey on secure outsourced computation and its applications (17), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (12), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (7), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (2), Homomorphic encryption standard (1), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (1), Security guidelines for implementing homomorphic encryption (1), SPIRAL: Fast, high-rate single-server PIR via FHE composition (1), Private machine learning classification based on fully homomorphic encryption (1), Secure federated learning applied to medical imaging with fully homomorphic encryption (1), Delphi: A Cryptographic Inference Service for Neural Networks (1)

GAN (10 papers)

FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (2), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (1), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1), SoK: Privacy-preserving computation techniques for deep learning (1), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), Efficiency Optimization Techniques in Privacy-Preserving Federated Learning With Homomorphic Encryption: A Brief Survey (1), An Efficient Architecture for Edge AI Federated Learning With Homomorphic Encryption (1), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (1), Application of Machine Learning-NLP Approach with Fully Homomorphic Encryption Techniques in Medical PII Data (1), Private pathological assessment via machine learning and homomorphic encryption (1)

Gradient boosting / XGBoost (10 papers)

Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (41), Efficiency Optimization Techniques in Privacy-Preserving Federated Learning With Homomorphic Encryption: A Brief Survey (8), HEonGPU: a GPU-based Fully Homomorphic Encryption Library 1.0 (6), Application of Machine Learning-NLP Approach with Fully Homomorphic Encryption Techniques in Medical PII Data (5), Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (4), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (3), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (2), BLEACH: Cleaning Errors in Discrete Computations over CKKS (2), SoK: Connecting the dots in privacy-preserving ML - systematization of MPC protocols and conversions between secret sharing schemes (1), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (1)

k-means (9 papers)

PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (24), A comprehensive survey on secure outsourced computation and its applications (18), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (7), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (4), ABY3: A Mixed Protocol Framework for Machine Learning (3), Large language model inference acceleration: A comprehensive hardware perspective (1), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (1), Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (1), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (1)

Mixture of experts (8 papers)

Integrating large language models in financial investments and market analysis: A survey (7), Large language model inference acceleration: A comprehensive hardware perspective (6), fairseq: A fast, extensible toolkit for sequence modeling (2), Attention is all you need (2), Iron: Private Inference on Transformers (2), Fully Homomorphic Encryption on the Ring of Gaussian Periods (1), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (1), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (1)

Naive Bayes (7 papers)

Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (13), A comprehensive survey on secure outsourced computation and its applications (9), Recursive deep models for semantic compositionality over a sentiment treebank (3), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (1), Private machine learning classification based on fully homomorphic encryption (1), Over 100x Faster Bootstrapping in Fully Homomorphic Encryption through Memory-centric Optimization with GPUs (1)

Random forest (7 papers)

Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (6), Integrating large language models in financial investments and market analysis: A survey (2), Building Privacy-Preserving AI system: AI Inference on Encrypted Data with Fully Homomorphic Encryption (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (1), Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (1), CipherGPT: Secure Two-Party GPT Inference (1)

GNN (5 papers)

Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering (65), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (1), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (1), FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System (1), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (1)

Diffusion model (3 papers)

Secure numerical simulations using fully homomorphic encryption (2), Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage (1), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1)

Spiking neural network (2 papers)

Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (22), SpyKing—Privacy-preserving framework for Spiking Neural Networks (22)