Skip to content

Browse by dataset

Declared in extracted details

Values reported by the structured extraction (field datasets).

Mentions in full text

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

MNIST (58 papers)

Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (63), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (25), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (23), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (22), Fully Homomorphic Encryption for Machine Learning (18), FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (17), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (17), Private and reliable neural network inference (16), Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning (15), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (14), Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities (14), Secure outsourced matrix computation and application to neural networks (12), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (11), HHEML: Hybrid Homomorphic Encryption for Privacy-Preserving Machine Learning on Edge (10), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (10), Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (10), HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models (9), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (9), Efficient Homomorphic Evaluation on Large Intervals (9), Homomorphic Encryption for Machine Learning and Artificial Intelligence Applications (8), ABY3: A Mixed Protocol Framework for Machine Learning (7), Towards Case-Optimized Hybrid Homomorphic Encryption (6), Private pathological assessment via machine learning and homomorphic encryption (6), TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption (6), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (6), On Fully Homomorphic Encryption for Privacy-Preserving Deep Learning (5), An Efficient and Privacy-Preserving Federated Learning Approach Based on Homomorphic Encryption (5), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (5), Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption (4), Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption (4), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (4), Federated Learning: An approach with Hybrid Homomorphic Encryption (4), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), Fully Homomorphic Encryption with Applications to Privacy-Preserving Machine Learning (3), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (3), Over 100x Faster Bootstrapping in Fully Homomorphic Encryption through Memory-centric Optimization with GPUs (3), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (3), Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks (3), High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function (3), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), Fully Homomorphically Encrypted Deep Learning as a Service (2), SpyKing—Privacy-preserving framework for Spiking Neural Networks (2), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (2), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (2), Secure human action recognition by encrypted neural network inference (2), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (2), CrypTFlow2: Practical 2-Party Secure Inference (2), SoK: Privacy-preserving computation techniques for deep learning (1), Machine Learning Training on Encrypted Data with TFHE (1), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (1), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (1), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (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), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (1), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (1), CrypTen: Secure Multi-Party Computation Meets Machine Learning (1), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (1)

CIFAR-10 (43 papers)

Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (45), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (19), BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption (19), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (18), FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (17), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (15), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (12), PPFLHE: A privacy-preserving federated learning scheme with homomorphic encryption for healthcare data (9), Orion: A Fully Homomorphic Encryption Framework for Deep Learning (9), Delphi: A Cryptographic Inference Service for Neural Networks (8), SoK: Private transformer-based model inference (6), Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption (6), GAZELLE: A Low Latency Framework for Secure Neural Network Inference (6), Converting transformers to polynomial form for secure inference over homomorphic encryption (6), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (5), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (5), Federated Learning with Quantum Computing and Fully Homomorphic Encryption: A Novel Computing Paradigm Shift in Privacy-Preserving ML (5), EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation (5), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (4), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (3), F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (3), DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption (3), Fully Homomorphically Encrypted Deep Learning as a Service (2), SpyKing—Privacy-preserving framework for Spiking Neural Networks (2), Private pathological assessment via machine learning and homomorphic encryption (2), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (1), Private and reliable neural network inference (1), Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption (1), Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference (1), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (1), Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning (1), Secure human action recognition by encrypted neural network inference (1), An Efficient Architecture for Edge AI Federated Learning With Homomorphic Encryption (1), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (1), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (1), Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures (1), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (1), Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (1), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (1), CipherGPT: Secure Two-Party GPT Inference (1), CrypTFlow2: Practical 2-Party Secure Inference (1), A scalable multi-GPU framework for encrypted large-model inference (1)

GLUE tasks (QNLI/RTE/MRPC/CoLA/QQP/MNLI/STS-B) (40 papers)

SoK: Private transformer-based model inference (117), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (61), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (47), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (41), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (38), BERT: Pre-training of deep bidirectional transformers for language understanding (37), Improving language understanding by generative pretraining (32), GLUE: A multi-task benchmark and analysis platform for natural language understanding (28), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (28), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (28), SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC (26), Encryption-friendly LLM architecture (26), Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference (21), THEMIS: A Co-Designed System for Encrypted Transformer Inference (18), PUMA: Secure Inference of LLaMA-7B in Five Minutes (17), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (14), Nimbus: Secure and Efficient Two-Party Inference for Transformers (14), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (14), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (12), ARION: Attention-optimized transformer inference on encrypted data (12), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (11), Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption (11), SIGMA: Secure GPT Inference with Function Secret Sharing (8), Iron: Private Inference on Transformers (8), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (8), STIP: Efficient and secure non-interactive transformer inference via compact packing (8), BumbleBee: Secure Two-party Inference Framework for Large Transformers (7), Secure transformer inference made non-interactive (7), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (6), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (6), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (5), SoK: Private LLM Inference using Approximate Homomorphic Encryption (5), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (4), THOR: Secure transformer inference with homomorphic encryption (4), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (3), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (3), Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache (2), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (1), Zephyr: GPU-Efficient Homomorphic Encryption for Privacy-Preserving Transformer Inference (1), A scalable multi-GPU framework for encrypted large-model inference (1)

ImageNet (35 papers)

Orion: A Fully Homomorphic Encryption Framework for Deep Learning (20), CrypTFlow2: Practical 2-Party Secure Inference (15), Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption (13), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (11), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (10), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (10), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (9), Converting transformers to polynomial form for secure inference over homomorphic encryption (8), Theory, analysis, and best practices for sigmoid selfattention (7), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (6), BumbleBee: Secure Two-party Inference Framework for Large Transformers (6), Neuracrypt is not private (5), SoK: Private transformer-based model inference (5), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (5), Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (4), Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives (3), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (3), DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption (3), Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network (3), CrypTen: Secure Multi-Party Computation Meets Machine Learning (3), SQuAD: 100,000+ questions for machine comprehension of text (2), ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse (2), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2), BERT: Pre-training of deep bidirectional transformers for language understanding (1), Privft: Private and fast text classification with homomorphic encryption (1), Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs (1), Secure federated learning applied to medical imaging with fully homomorphic encryption (1), BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption (1), Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library (1), HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (1), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (1), MP-SPDZ: A Versatile Framework for Multi-Party Computation (1), SIGMA: Secure GPT Inference with Function Secret Sharing (1), Secure transformer inference made non-interactive (1), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (1)

SST-2 (33 papers)

SoK: Private transformer-based model inference (37), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (26), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (16), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (12), SoK: Private LLM Inference using Approximate Homomorphic Encryption (10), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (8), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (8), THEMIS: A Co-Designed System for Encrypted Transformer Inference (8), Encryption-friendly LLM architecture (7), Improving language understanding by generative pretraining (5), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (5), ARION: Attention-optimized transformer inference on encrypted data (5), BERT: Pre-training of deep bidirectional transformers for language understanding (4), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (4), SIGMA: Secure GPT Inference with Function Secret Sharing (4), STIP: Efficient and secure non-interactive transformer inference via compact packing (4), Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption (4), GLUE: A multi-task benchmark and analysis platform for natural language understanding (3), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (3), Secure transformer inference made non-interactive (3), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (3), TRICYCLE: Private transformer inference with tricyclic encodings (3), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (3), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), Nimbus: Secure and Efficient Two-Party Inference for Transformers (2), Iron: Private Inference on Transformers (2), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (2), THOR: Secure transformer inference with homomorphic encryption (2), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (1), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (1), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (1), Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference (1), Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference (1)

GLUE (30 papers)

BERT: Pre-training of deep bidirectional transformers for language understanding (20), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (19), MPCFormer: Fast, Performant and Private Transformer Inference with MPC (14), SoK: Private LLM Inference using Approximate Homomorphic Encryption (14), GLUE: A multi-task benchmark and analysis platform for natural language understanding (13), EncFormer: Secure and Efficient Transformer Inference over Encrypted Data (7), ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference (6), Improving language understanding by generative pretraining (5), SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference (5), Nimbus: Secure and Efficient Two-Party Inference for Transformers (5), THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (5), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (5), Ditto: Quantization-aware Secure Inference of Transformers upon MPC (4), BumbleBee: Secure Two-party Inference Framework for Large Transformers (4), PUMA: Secure Inference of LLaMA-7B in Five Minutes (3), STIP: Efficient and secure non-interactive transformer inference via compact packing (3), Powerformer: Efficient and high-accuracy privacy-preserving language model with homomorphic encryption (3), Encryption-friendly LLM architecture (3), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2), SIGMA: Secure GPT Inference with Function Secret Sharing (2), Iron: Private Inference on Transformers (2), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (2), THEMIS: A Co-Designed System for Encrypted Transformer Inference (2), Secure transformer inference made non-interactive (2), MOAI: Module-optimizing architecture for non-interactive secure transformer inference (2), Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity (2), A scalable multi-GPU framework for encrypted large-model inference (2), THOR: Secure transformer inference with homomorphic encryption (2), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (1), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (1)

Breast cancer (Wisconsin) (13 papers)

Secure federated learning applied to medical imaging with fully homomorphic encryption (17), Private pathological assessment via machine learning and homomorphic encryption (11), Practical Considerations of Fully Homomorphic Encryption in Privacy-Preserving Machine Learning (6), Non-interactive Fully Encrypted Machine Learning Protocol for Inference (4), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (4), Stealing machine learning models via prediction APIs (2), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (2), 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), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (1), Private machine learning classification based on fully homomorphic encryption (1), SecretFlow-SPU: A Performant and User-Friendly Framework for Privacy-Preserving Machine Learning (1), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (1)

UCI repository (11 papers)

SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (5), Non-interactive Fully Encrypted Machine Learning Protocol for Inference (5), Stealing machine learning models via prediction APIs (4), Private pathological assessment via machine learning and homomorphic encryption (3), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (2), Privft: Private and fast text classification with homomorphic encryption (1), Private machine learning classification based on 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), Practical Privacy-Preserving Machine Learning using Fully Homomorphic Encryption (1), Secure Federated Learning With Fully Homomorphic Encryption for IoT Communications (1)

CIFAR-100 (10 papers)

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users (21), Converting transformers to polynomial form for secure inference over homomorphic encryption (8), Delphi: A Cryptographic Inference Service for Neural Networks (7), SoK: Private transformer-based model inference (5), Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption (3), 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), Fully Homomorphically Encrypted Deep Learning as a Service (1), CipherGPT: Secure Two-Party GPT Inference (1), CrypTFlow2: Practical 2-Party Secure Inference (1)

IMDB (10 papers)

MPCFormer: Fast, Performant and Private Transformer Inference with MPC (14), CRAfT: Constant-Round Non-Polynomial Approximation and P2P Network for Secure Transformer Inference (7), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (4), Privft: Private and fast text classification with homomorphic encryption (4), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (3), ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour (2), [Skyformer: Remodel selfattention with gaussian kernel and nystr](../papers/skyformer-remodel-selfattention-with-gaussian-kernel-and-nystr.md) (1), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1), SoK: Private transformer-based model inference (1), A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption (1)

ARC (9 papers)

Think you have solved question answering? try ARC, the AI2 reasoning challenge (62), GPT-4 System Card (11), Theory, analysis, and best practices for sigmoid selfattention (5), Llama: Open and efficient foundation language models (3), SoK: Private transformer-based model inference (3), Fully Homomorphic Encryption with Chosen-Ciphertext Security from LWE (3), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (3), SoK: Private LLM Inference using Approximate Homomorphic Encryption (2), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (1)

WikiText (9 papers)

Pointer sentinel mixture models (24), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (5), An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference (4), fairseq: A fast, extensible toolkit for sequence modeling (3), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (2), SoK: Private transformer-based model inference (2), Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (1), CipherGPT: Secure Two-Party GPT Inference (1), Converting transformers to polynomial form for secure inference over homomorphic encryption (1)

HellaSwag (8 papers)

HellaSwag: Can a machine really finish your sentence? (25), PrivateLoRA for Efficient Privacy Preserving LLM (4), Llama: Open and efficient foundation language models (3), HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation (2), EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption (2), SoK: Private LLM Inference using Approximate Homomorphic Encryption (2), Bitnet: Scaling 1-bit transformers for large language models (1), CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption (1)

Iris (8 papers)

Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (13), Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption (12), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (11), Non-interactive Fully Encrypted Machine Learning Protocol for Inference (5), Stealing machine learning models via prediction APIs (4), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (3), PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption (2), Cost-efficient llm training with lifetimeaware tensor offloading via gpudirect storage (1)

Credit card / German credit (7 papers)

Private svm inference on encrypted data (8), Stealing machine learning models via prediction APIs (5), SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (1), ABY3: A Mixed Protocol Framework for Machine Learning (1), Fully Homomorphic Encryption for Machine Learning (1), Fully Homomorphic Encryption with Applications to Privacy-Preserving Machine Learning (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)

SQuAD (7 papers)

SQuAD: 100,000+ questions for machine comprehension of text (21), BERT: Pre-training of deep bidirectional transformers for language understanding (19), Think you have solved question answering? try ARC, the AI2 reasoning challenge (8), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (3), GLUE: A multi-task benchmark and analysis platform for natural language understanding (2), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1), SoK: Private LLM Inference using Approximate Homomorphic Encryption (1)

Fingerprint (FVC) (6 papers)

Touch of Privacy: A Homomorphic Encryption-Powered Deep Learning Framework for Fingerprint Authentication (133), Enhancing privacy-preserving machine learning with self-learnable activation functions in fully homomorphic encryption (3), Approximate homomorphic encryption based privacy-preserving machine learning: a survey (2), Homomorphic encryption standard (1), A comprehensive survey on secure outsourced computation and its applications (1), Rubato : Noisy Ciphers for Approximate Homomorphic Encryption (Full Version) (1)

LAMBADA (5 papers)

The LAMBADA dataset: Word prediction requiring a broad discourse context (69), ROSETTA: Efficient and Accurate Privacy-Preserving LLM Decoding via Hybrid CKKS/TFHE Evaluation (4), Theory, analysis, and best practices for sigmoid selfattention (2), SIGMA: Secure GPT Inference with Function Secret Sharing (1), SoK: Private LLM Inference using Approximate Homomorphic Encryption (1)

Yelp (5 papers)

SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (6), Privft: Private and fast text classification with homomorphic encryption (4), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (3), CrypTen: Secure Multi-Party Computation Meets Machine Learning (3), SoK: Private transformer-based model inference (1)

Chest X-ray (4 papers)

Private pathological assessment via machine learning and homomorphic encryption (4), A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (1), Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (1), CrypTFlow2: Practical 2-Party Secure Inference (1)

COVID (4 papers)

HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data (7), Large language models in medicine (2), Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (2), Secure Federated Learning With Fully Homomorphic Encryption for IoT Communications (1)

Penn Treebank (4 papers)

Pointer sentinel mixture models (28), SQuAD: 100,000+ questions for machine comprehension of text (2), Automatically constructing a corpus of sentential paraphrases (1), Attention is all you need (1)

AG News (3 papers)

SoK: Wildest dreams: Reproducible research in privacy-preserving neural network training (4), Split-and-Denoise: Protect Large Language Model Inference with Local Differential Privacy (4), Privft: Private and fast text classification with homomorphic encryption (3)

Diabetes (Pima) (3 papers)

Private pathological assessment via machine learning and homomorphic encryption (6), Homomorphic Encryption for Arithmetic of Approximate Numbers (3), Stealing machine learning models via prediction APIs (2)

ECG (3 papers)

Private pathological assessment via machine learning and homomorphic encryption (2), Fully Homomorphic Encryption with Applications to Privacy-Preserving Machine Learning (1), BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers (1)

Heart disease (3 papers)

Exploring the future of privacy-preserving heart disease prediction: a fully homomorphic encryption-driven logistic regression approach (12), Private pathological assessment via machine learning and homomorphic encryption (11), Homomorphic Encryption for Machine Learning in Medicine and Bioinformatics (2)

MedMNIST (3 papers)

A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference (37), Private pathological assessment via machine learning and homomorphic encryption (11), Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions (1)

Fashion-MNIST (2 papers)

SpyKing—Privacy-preserving framework for Spiking Neural Networks (2), Towards Case-Optimized Hybrid Homomorphic Encryption (1)

Phishing (2 papers)

GPT-4 System Card (6), Pasta: A Case for Hybrid Homomorphic Encryption (1)

SVHN (2 papers)

An Efficient and Privacy-Preserving Federated Learning Approach Based on Homomorphic Encryption (3), SoK: Private transformer-based model inference (1)

Action recognition (UCF/HMDB/KTH) (1 papers)

Secure human action recognition by encrypted neural network inference (2)

Adult (census income) (1 papers)

Private and reliable neural network inference (2)

Cora / Citeseer / PubMed (graphs) (1 papers)

Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption (1)