Papers by author
- Jung Ho Ahn (5): 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); Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures; BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption; ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse; SHARP: A Short-Word Hierarchical Accelerator for Robust and Practical Fully Homomorphic Encryption
- A. Alexandru (2): General Functional Bootstrapping using CKKS; Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption
- Hisham Ali (2): Evaluation of Privacy-aware Support Vector Machine (SVM) Learning using Homomorphic Encryption; Evaluation of Privacy-Preserving Support Vector Machine (SVM) Learning Using Homomorphic Encryption
- Khin Mi Mi Aung (4): EncFormer: Secure and Efficient Transformer Inference over Encrypted Data; Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs; DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption; Privft: Private and fast text classification with homomorphic encryption
- Mikhail Babenko (2): A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
- A. Al Badawi (2): OpenFHE: Open-Source Fully Homomorphic Encryption Library; Private svm inference on encrypted data
- Ahmad Al Badawi (3): TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation; Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs; Privft: Private and fast text classification with homomorphic encryption
- A. A. Badawi (2): Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption; Demystifying bootstrapping in fully homomorphic encryption
- Moran Baruch (2): Converting transformers to polynomial form for secure inference over homomorphic encryption; HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
- Dan Boneh (2): Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware; Evaluating 2-DNF Formulas on Ciphertexts
- Z. Brakerski (2): (Leveled) Fully Homomorphic Encryption without Bootstrapping; Fully Homomorphic Encryption without Modulus Switching from Classical GapSVP
- Hao Chen (3): Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference; Improved Bootstrapping for Approximate Homomorphic Encryption; High-Precision Arithmetic in Homomorphic Encryption
- Y. Chen (2): SoK: Private transformer-based model inference; Towards efficient privacy-preserving machine learning: A systematic review from protocol, model, and system perspectives
- Jung Hee Cheon (7): 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); Encryption-friendly LLM architecture; Homomorphic Encryption for Arithmetic of Approximate Numbers; Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused; Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS; Efficient Homomorphic Evaluation on Large Intervals; Privacy-preserving computations of predictive medical models with minimax approximation and non-adjacent form
- I. Chillotti (2): TFHE Gets Real: An Efficient and Flexible Homomorphic Floating-Point Arithmetic; Security guidelines for implementing homomorphic encryption
- Wonhee Cho (2): Fast and Accurate Homomorphic Softmax Evaluation; Heracles: 8192-way simd programmable scalable fully-homomorphic encryption soc for privacy-preserving cloud computing in intel 3 cmos
- Hyeongmin Choe (3): Leveraging Discrete CKKS to Bootstrap in High Precision; Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS; Stay in Your Lane: Fast Arithmetic over Large Finite Rings with CKKS
- Sherman S. M. Chow (2): SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference; SoK: Cryptographic neural-network computation
- Jorge M. Cortés-Mendoza (2): A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
- B. R. Curtis (2): Security guidelines for implementing homomorphic encryption; On the precision loss in approximate homomorphic encryption
- W. Dai (3): ARION: Attention-optimized transformer inference on encrypted data; Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library; Security guidelines for implementing homomorphic encryption
- Wei Dai (2): Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference; EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation
- Maxim Deryabin (2): Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption
- Srinivas Devadas (2): A Tensor Compiler with Automatic Data Packing for Simple and Efficient Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- Li Dong (2): THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption; Bitnet: Scaling 1-bit transformers for large language models
- Ye Dong (2): PUMA: Secure Inference of LLaMA-7B in Five Minutes; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Nir Drucker (2): Converting transformers to polynomial form for secure inference over homomorphic encryption; HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
- Karim Eldefrawy (2): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- Jieun Eom (2): Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption
- Gilad Ezov (2): Converting transformers to polynomial form for secure inference over homomorphic encryption; HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
- Axel Feldmann (2): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- S. Fu (2): Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; STIP: Efficient and secure non-interactive transformer inference via compact packing
- X. Gao (2): Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; STIP: Efficient and secure non-interactive transformer inference via compact packing
- Robin Geelen (2): BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption; Bootstrapping for BGV and BFV Revisited
- N. Genise (2): OpenFHE: Open-Source Fully Homomorphic Encryption Library; Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption
- Nicholas Genise (2): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- C. Gentry (2): Fully Homomorphic Encryption for Matrix Arithmetic; (Leveled) Fully Homomorphic Encryption without Bootstrapping
- Craig Gentry (2): Efficient Bootstrapping in Fully Homomorphic Encryption for Matrix Arithmetic; Fully Homomorphic Encryption Using Ideal Lattices
- S. Goldwasser (2): Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption; Homomorphic encryption standard
- E. Hales (2): Security guidelines for implementing homomorphic encryption; On the precision loss in approximate homomorphic encryption
- S. Halevi (3): OpenFHE: Open-Source Fully Homomorphic Encryption Library; Algorithms in HElib; Homomorphic encryption standard
- Guillaume Hanrot (3): 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); Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused; Fast and Accurate Homomorphic Softmax Evaluation
- Cheng Hong (3): PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption; PUMA: Secure Inference of LLaMA-7B in Five Minutes; Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption
- Zhicong Huang (2): PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption; PUMA: Secure Inference of LLaMA-7B in Five Minutes
- Shaohan Huang (2): THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption; Bitnet: Scaling 1-bit transformers for large language models
- X. Jiang (2): THOR: Secure transformer inference with homomorphic encryption; Secure outsourced matrix computation and application to neural networks
- Chao Jin (2): EncFormer: Secure and Efficient Transformer Inference over Encrypted Data; Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs
- M. Kim (2): THOR: Secure transformer inference with homomorphic encryption; Secure outsourced matrix computation and application to neural networks
- Jung Woo Kim (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); Encryption-friendly LLM architecture
- J. Kim (2): ELLMo: Packing- and Depth-Aware Encrypted Transformer Inference; SHIP: A Shallow and Highly Parallelizable CKKS Bootstrapping Algorithm
- Taeseong Kim (2): Encryption-friendly LLM architecture; Fast and Accurate Homomorphic Softmax Evaluation
- Young-Sik Kim (3): CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption; High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function; Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network
- Andrey Kim (2): Homomorphic Encryption for Arithmetic of Approximate Numbers; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption
- Miran Kim (3): Homomorphic Encryption for Arithmetic of Approximate Numbers; Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference; Secure human action recognition by encrypted neural network inference
- D. Kim (3): Approximate Homomorphic Encryption over the Conjugate-invariant Ring; DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption; Security guidelines for implementing homomorphic encryption
- A. Kim (2): General Functional Bootstrapping using CKKS; OpenFHE: Open-Source Fully Homomorphic Encryption Library
- Jaehyung Kim (2): Leveraging Discrete CKKS to Bootstrap in High Precision; Grafting: Decoupled Scale Factors and Modulus in RNS-CKKS
- Jongmin Kim (4): Cheddar: A Swift Fully Homomorphic Encryption Library Designed for GPU Architectures; BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption; ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse; SHARP: A Short-Word Hierarchical Accelerator for Robust and Practical Fully Homomorphic Encryption
- Sangpyo Kim (3): BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption; ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse; SHARP: A Short-Word Hierarchical Accelerator for Robust and Practical Fully Homomorphic Encryption
- John Kim (2): BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption; ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse
- Aleksandar Krastev (3): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; A Tensor Compiler with Automatic Data Packing for Simple and Efficient Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- Kim Laine (3): High-Precision Arithmetic in Homomorphic Encryption; EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation; Privft: Private and fast text classification with homomorphic encryption
- Yongwoo Lee (5): CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption; High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function; Efficient Bootstrapping in Fully Homomorphic Encryption for Matrix Arithmetic; Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption
- Joon-Woo Lee (2): High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function; Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network
- Eunsang Lee (2): High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function; Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network
- Y. Lee (3): Fully Homomorphic Encryption for Matrix Arithmetic; OpenFHE: Open-Source Fully Homomorphic Encryption Library; DaCapo: Automatic Bootstrapping Management for Efficient Fully Homomorphic Encryption
- Meng Li (2): Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache; Swift: Fast Secure Neural Network Inference With Fully Homomorphic Encryption
- Dacheng Li (2): MPCFormer: Fast, Performant and Private Transformer Inference with MPC; MPC-Minimized Secure LLM Inference
- L. Liu (2): Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; STIP: Efficient and secure non-interactive transformer inference via compact packing
- Z. Liu (3): Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; Phantom: A CUDA-Accelerated Word-Wise Homomorphic Encryption Library; Secretvoice1.0: Non-interactive secure transformer inference
- Shiyu Liu (2): Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Wen-jie Lu (3): PEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption; PUMA: Secure Inference of LLaMA-7B in Five Minutes; Nimbus: Secure and Efficient Two-Party Inference for Transformers
- Jinglong Luo (3): SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- D. Micciancio (3): On the Security of Homomorphic Encryption on Approximate Numbers; Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption; Homomorphic encryption standard
- Seo, Min (2): Zephyr: GPU-Efficient Homomorphic Encryption for Privacy-Preserving Transformer Inference; Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference
- Chan Fook Mun (3): Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs; DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption; Privft: Private and fast text classification with homomorphic encryption
- Jong-Seon No (2): High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function; Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network
- Jaiyoung Park (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); SHARP: A Short-Word Hierarchical Accelerator for Robust and Practical Fully Homomorphic Encryption
- Jai Hyun Park (3): 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); Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused; Efficient Homomorphic Evaluation on Large Intervals
- Minje Park (3): 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); Encryption-friendly LLM architecture; Fast and Accurate Homomorphic Softmax Evaluation
- Jeongeun Park (2): FINAL: Faster FHE Instantiated with NTRU and LWE; FINALLY: A Multi-Key FHE Scheme Based on NTRU and LWE
- Chris Peikert (3): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; Faster bootstrapping with polynomial error; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- Hilder V. L. Pereira (2): FINAL: Faster FHE Instantiated with NTRU and LWE; BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption
- R. Player (2): Security guidelines for implementing homomorphic encryption; On the precision loss in approximate homomorphic encryption
- Y. Polyakov (4): General Functional Bootstrapping using CKKS; Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption; Demystifying bootstrapping in fully homomorphic encryption; Security guidelines for implementing homomorphic encryption
- Yuriy Polyakov (2): TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation; Secure numerical simulations using fully homomorphic encryption
- Gleb Radchenko (2): A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
- Brandon Reagen (2): Orion: A Fully Homomorphic Encryption Framework for Deep Learning; TREBUCHET: Fully Homomorphic Encryption Accelerator for Deep Computation
- Minsoo Rhu (2): BTS: An Accelerator for Bootstrappable Fully Homomorphic Encryption; ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse
- Nikola Samardzic (3): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; A Tensor Compiler with Automatic Data Packing for Simple and Efficient Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- Daniel Sanchez (3): F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption; A Tensor Compiler with Automatic Data Packing for Simple and Efficient Fully Homomorphic Encryption; CraterLake: A Hardware Accelerator for Efficient Unbounded Computation on Encrypted Data
- Muhammad Shafique (2): Federated Learning with Quantum Computing and Fully Homomorphic Encryption: A Novel Computing Paradigm Shift in Privacy-Preserving ML; SpyKing—Privacy-preserving framework for Spiking Neural Networks
- Omri Soceanu (2): Converting transformers to polynomial form for secure inference over homomorphic encryption; HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data
- Yongsoo Song (3): Homomorphic Encryption for Arithmetic of Approximate Numbers; Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference; Improved Bootstrapping for Approximate Homomorphic Encryption
- Cheon, Han, Kim, Kim, Song (2): A Full RNS Variant of Approximate Homomorphic Encryption; Bootstrapping for Approximate Homomorphic Encryption
- Y. Song (3): Approximate Homomorphic Encryption over the Conjugate-invariant Ring; Security guidelines for implementing homomorphic encryption; Secure outsourced matrix computation and application to neural networks
- Damien Stehlé (4): 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); Leveraging Discrete CKKS to Bootstrap in High Precision; Plaintext-Ciphertext Matrix Multiplication and FHE Bootstrapping: Fast and Fused; Fast and Accurate Homomorphic Softmax Evaluation
- Jin Tan (3): PUMA: Secure Inference of LLaMA-7B in Five Minutes; Nimbus: Secure and Efficient Two-Party Inference for Transformers; Ditto: Quantization-aware Secure Inference of Transformers upon MPC
- Benjamin Hong Meng Tan (2): Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs; DOReN: Toward Efficient Deep Convolutional Neural Networks with Fully Homomorphic Encryption
- Andrei Tchernykh (2): A Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption; Privacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
- Florian Tramèr (2): Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware; Stealing machine learning models via prediction APIs
- Shokri, Tsoutsos (2): Terrazzo: Memory-Aware GPU Framework for Private Transformer Inference; Low-Depth Bootstrapping for Matrix-Native FHE
- V. Vaikuntanathan (4): (Leveled) Fully Homomorphic Encryption without Bootstrapping; Collaborative privacy-preserving analysis of oncological data using multiparty homomorphic encryption; One server for the price of two: Simple and fast single-server private information retrieval; Homomorphic encryption standard
- Martin Vechev (2): Beyond memorization: Violating privacy via inference with large language models; Private and reliable neural network inference
- Frederik Vercauteren (2): BASALISC: Programmable Hardware Accelerator for BGV Fully Homomorphic Encryption; Bootstrapping for BGV and BFV Revisited
- Y. Wang (3): Euston: Efficient and User-Friendly Secure Transformer Inference with Non-Interactivity; Secure transformer inference made non-interactive; STIP: Efficient and secure non-interactive transformer inference via compact packing
- Z. Wang (2): STIP: Efficient and secure non-interactive transformer inference via compact packing; SoK: Private transformer-based model inference
- Hui Wang (3): SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Furu Wei (2): THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption; Bitnet: Scaling 1-bit transformers for large language models
- Haoqi Wu (3): PUMA: Secure Inference of LLaMA-7B in Five Minutes; Nimbus: Secure and Efficient Two-Party Inference for Transformers; Ditto: Quantization-aware Secure Inference of Transformers upon MPC
- Zenglin Xu (3): SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Donghoon Yoo (2): Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network; Efficient FHEW Bootstrapping with Small Evaluation Keys, and Applications to Threshold Homomorphic Encryption
- Yue Yu (3): SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Zama (2): TFHE-rs: Pure Rust implementation of TFHE; Concrete ML: Privacy-Preserving ML with FHE
- Hao Zhang (2): MPCFormer: Fast, Performant and Private Transformer Inference with MPC; MPC-Minimized Secure LLM Inference
- Yehong Zhang (3): SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Zhuo Zhang (2): SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions
- Derun Zhao (2): PUMA: Secure Inference of LLaMA-7B in Five Minutes; Nimbus: Secure and Efficient Two-Party Inference for Transformers
- Wenting Zheng (2): A scalable multi-GPU framework for encrypted large-model inference; Delphi: A Cryptographic Inference Service for Neural Networks
- Yancheng Zheng (3): PUMA: Secure Inference of LLaMA-7B in Five Minutes; Nimbus: Secure and Efficient Two-Party Inference for Transformers; Ditto: Quantization-aware Secure Inference of Transformers upon MPC
- Xun Zhou (2): Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference; Cryptography-based privacy-preserving large language models: a lifecycle survey of frameworks, methods, and future directions