{"id":13487419,"url":"https://github.com/Ye-D/PPML-Resource","last_synced_at":"2025-03-27T22:31:06.731Z","repository":{"id":38393782,"uuid":"187940291","full_name":"Ye-D/PPML-Resource","owner":"Ye-D","description":"Materials about Privacy-Preserving Machine Learning ","archived":false,"fork":false,"pushed_at":"2024-06-26T15:15:06.000Z","size":58,"stargazers_count":220,"open_issues_count":0,"forks_count":51,"subscribers_count":12,"default_branch":"master","last_synced_at":"2024-08-01T18:30:12.916Z","etag":null,"topics":["deep-learning","machine-learning","mpc","privacy","secure-computation"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ye-D.png","metadata":{"files":{"readme":"ReadMe.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-05-22T01:32:33.000Z","updated_at":"2024-07-23T01:25:46.000Z","dependencies_parsed_at":"2023-02-02T12:45:23.286Z","dependency_job_id":"4c13ba28-ab5f-46e4-acf7-4e65ff777bc2","html_url":"https://github.com/Ye-D/PPML-Resource","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ye-D%2FPPML-Resource","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ye-D%2FPPML-Resource/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ye-D%2FPPML-Resource/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ye-D%2FPPML-Resource/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ye-D","download_url":"https://codeload.github.com/Ye-D/PPML-Resource/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222322034,"owners_count":16966433,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","machine-learning","mpc","privacy","secure-computation"],"created_at":"2024-07-31T18:00:59.050Z","updated_at":"2025-03-27T22:31:06.706Z","avatar_url":"https://github.com/Ye-D.png","language":null,"funding_links":[],"categories":["Privacy Lists"],"sub_categories":[],"readme":"# Privacy-Preserving-Machine-Learning-Resources\r\n\r\n## Content\r\n- [Privacy-Preserving-Machine-Learning-Resources](#privacy-preserving-machine-learning-resources)\r\n  - [Content](#content)\r\n- [About](#about)\r\n- [Secure Machine Learning](#secure-machine-learning)\r\n- [MPC](#mpc)\r\n- [Zero Knowledge for Machine Learning](#zero-knowledge-for-machine-learning)\r\n- [Federated Learning](#federated-learning)\r\n  - [Secure Federated Learning](#secure-federated-learning)\r\n  - [Communication Optimization](#communication-optimization)\r\n  - [Byzantine-Tolerant](#byzantine-tolerant)\r\n- [Privacy Leakages of ML/FL](#privacy-leakages-of-mlfl)\r\n- [Blogs](#blogs)\r\n- [Libraries and Frameworks](#libraries-and-frameworks)\r\n\r\n\r\n# About\r\nThis is a current list of resources related to the research and development of privacy-preserving machine learning.\r\n\r\n\r\n# Secure Machine Learning\r\n* [安全多方计算及其在机器学习中的应用, 计算机研究与发展'21](https://crad.ict.ac.cn/CN/10.7544/issn1000-1239.2021.20210626)\r\n* [Machine Learning Classification over Encrypted Data, NDSS'14](https://eprint.iacr.org/2014/331.pdf)\r\n* [Oblivious Multi-Party Machine Learning on Trusted Processors, USENIX SECURITY'16](https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/ohrimenko)\r\n* [SecureML: A System for Scalable Privacy-Preserving Machine Learning, S\u0026P'17](https://eprint.iacr.org/2017/396)\r\n* [MiniONN: Oblivious Neural Network Predictions via MiniONN Transformations, CCS'17](https://acmccs.github.io/papers/p619-liuA.pdf)\r\n* [Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications, AsiaCCS'17](https://eprint.iacr.org/2017/1164)\r\n* [DeepSecure: Scalable Provably-Secure Deep Learning, DAC'17](https://arxiv.org/abs/1705.08963)\r\n* [Secure Computation for Machine Learning With SPDZ, NIPS'18](https://arxiv.org/abs/1901.00329)\r\n* [ABY3:a Mixed protocol Framework for Machine Learning, CCS'18](https://eprint.iacr.org/2018/403.pdf)\r\n* [SecureNN: Efficient and Private Neural Network Training, PoPETs'18](https://eprint.iacr.org/2018/442.pdf)\r\n* [Gazelle: A Low Latency Framework for Secure Neural Network Inference, USENIX SECURITY'18](https://arxiv.org/abs/1801.05507)\r\n* [CHET: an optimizing compiler for fully-homomorphic neural-network inferencing, PLDI'19](https://dl.acm.org/citation.cfm?id=3314628)\r\n* [New Primitives for Actively-Secure MPC over Rings with Applications to Private Machine Learning, S\u0026P'19](https://eprint.iacr.org/2019/599.pdf)\r\n* [Helen: Maliciously Secure Coopetitive Learning for Linear Models, S\u0026P'19](https://ieeexplore.ieee.org/abstract/document/8835215)\r\n* [Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference. CCS'19](https://dl.acm.org/citation.cfm?id=3363207)\r\n* [XONN: XNOR-based Oblivious Deep Neural Network Inference, USENIX Security'19](https://www.usenix.org/conference/usenixsecurity19/presentation/riazi)\r\n* [QUOTIENT: two-party secure neural network training and prediction, CCS'19](https://dl.acm.org/citation.cfm?id=3339819)\r\n* [Secure Evaluation of Quantized Neural Networks, PoPETs'20](https://content.sciendo.com/view/journals/poPoPETs/2020/4/article-p355.xml)\r\n* [ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction, CCSW'19](https://eprint.iacr.org/2019/429)\r\n* [SoK: Modular and Efficient Private Decision Tree Evaluation, PoPETs'19](https://eprint.iacr.org/2018/1099.pdf)\r\n* [Trident: Efficient 4PC Framework for Privacy Preserving Machine Learning, NDSS'20](https://eprint.iacr.org/2019/1315)\r\n* [BLAZE: Blazing Fast Privacy-Preserving Machine Learning, NDSS'20](https://eprint.iacr.org/2020/042)\r\n* [FLASH: Fast and Robust Framework for Privacy-preserving Machine Learning, PoPETs'20](https://eprint.iacr.org/2019/1365)\r\n* [Delphi: A Cryptographic Inference Service for Neural Networks, USENIX SECURITY'20](https://eprint.iacr.org/2020/050)\r\n* [ParSecureML: An Efficient Parallel Secure Machine Learning Framework on GPUs, ICPP'20](https://dl.acm.org/doi/abs/10.1145/3404397.3404399)\r\n* [FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning, PoPETs'21](https://arxiv.org/abs/2004.02229)\r\n* [MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference, ARES'20](https://dl.acm.org/doi/abs/10.1145/3407023.3407045)\r\n* [SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search, USENIX Security'20](https://www.usenix.org/conference/usenixsecurity20/presentation/chen-hao)\r\n* [PySyft: A Generic Framework for Privacy Preserving Deep Learning](https://arxiv.org/abs/1811.04017)\r\n* [Private Deep Learning in TensorFlow Using Secure Computation](https://arxiv.org/abs/1810.08130)\r\n* [CryptoDL: Deep Neural Networks over Encrypted Data](https://arxiv.org/abs/1711.05189)\r\n* [CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/04/CryptonetsTechReport.pdf)\r\n* [CrypTFlow: Secure TensorFlow Inference](https://eprint.iacr.org/2019/1049.pdf)\r\n* [CrypTFlow2: Practical 2-Party Secure Inference, CCS'20](https://arxiv.org/abs/2010.06457)\r\n* [ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing](https://arxiv.org/abs/2006.04593)\r\n* [Practical Privacy-Preserving K-means Clustering, PoPETs'20](https://content.sciendo.com/view/journals/poPoPETs/2020/4/article-p414.xml)\r\n* [SOTERIA: In Search of Efficient Neural Networks for Private Inference, 20](https://arxiv.org/abs/2007.12934)\r\n* [SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning, USENIX Security'21](https://arxiv.org/abs/2005.10296)\r\n* [An Efficient 3-Party Framework for Privacy-Preserving Neural Network Inference, ESORICS'20](https://link.springer.com/chapter/10.1007/978-3-030-58951-6_21)\r\n* [Secure and Verifiable Inference in Deep Neural Networks, ACSAC'20](https://dl.acm.org/doi/abs/10.1145/3427228.3427232)\r\n* [Privacy-preserving Density-based Clustering, AisaCCS'21](https://www.eurecom.fr/publication/6475/download/sec-publi-6475.0.pdf)\r\n* [SIRNN: A Math Library for Secure RNN Inference, S\u0026P'21](https://eprint.iacr.org/2021/459)\r\n* [Let’s Stride Blindfolded in a Forest: Sublinear Multi-Client Decision Trees Evaluation, NDSS'21](https://www.ndss-symposium.org/ndss-paper/lets-stride-blindfolded-in-a-forest-sublinear-multi-client-decision-trees-evaluation/)\r\n* [MUSE: Secure Inference Resilient to Malicious Clients, USENIX Security'21](https://people.eecs.berkeley.edu/~raluca/MUSEcamera.pdf)\r\n* [DeepReDuce: ReLU Reduction for Fast Private Inference, ICML'21](https://arxiv.org/abs/2103.01396)\r\n* [Garbled Neural Networks are Practical](https://eprint.iacr.org/2019/338.pdf)\r\n* [GForce : GPU-Friendly Oblivious and Rapid Neural Network Inference, USENIX Security'21](https://www.usenix.org/conference/usenixsecurity21/presentation/ng)\r\n* [CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU, S\u0026P'21](http://arxiv.org/abs/2104.10949)\r\n* [GALA : Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks, NDSS'21](https://www.ndss-symposium.org/ndss-paper/gala-greedy-computation-for-linear-algebra-in-privacy-preserved-neural-networks/)\r\n* [Fantastic Four: Honest-Majority Four-Party Secure Computation With Malicious Security, USENIX Security'21](https://www.usenix.org/system/files/sec21fall-dalskov.pdf)\r\n* [When homomorphic encryption marries secret sharing: secure large-scale sparse logistic regression and applications in risk control, KDD'21](https://arxiv.org/abs/2008.08753)\r\n* [Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data, NeurIPS'20](https://arxiv.org/pdf/1911.07101.pdf)\r\n* [SoK: Efficient Privacy-preserving Clustering, PoPETs'21](https://eprint.iacr.org/2021/809)\r\n* [Secure Quantized Training for Deep Learning, ICML](https://arxiv.org/abs/2107.00501)\r\n* [Cerebro: A Platform for Multi-Party Cryptographic Collaborative Learning, USENIX Security'21](https://www.usenix.org/conference/usenixsecurity21/presentation/zheng)\r\n* [Tetrad: Actively Secure 4PC for Secure Training and Inference, NDSS'22](https://arxiv.org/abs/2106.02850)\r\n* [Adam in Private : Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimation, PoPETs'22](https://arxiv.org/abs/2106.02203)\r\n* [SIMC: ML Inference Secure Against Malicious Clients at Semi-Honest Cost, USENIX Security'22](https://www.usenix.org/conference/usenixsecurity22/presentation/chandran)\r\n* [Circa : Stochastic ReLUs for Private Deep Learning, NeurIPS'21](https://proceedings.neurips.cc/paper/2021/file/11eba2991cc62daa4a85be5c0cfdae97-Paper.pdf)\r\n* [Banners: Binarized Neural Networks with Replicated Secret Sharing, IH\u0026MMSec'21](https://dl.acm.org/doi/10.1145/3437880.3460394)\r\n* [Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference, USENIX Security'22](https://eprint.iacr.org/2022/207)\r\n* [Secure Poisson Regression, USENIX Security'22](https://www.usenix.org/conference/usenixsecurity22/presentation/kelkar)\r\n* [SecFloat: Accurate Floating-Point meets Secure 2-Party Computation, S\u0026P'22](https://eprint.iacr.org/2022/322)\r\n* [MPClan: Protocol Suite for Privacy-Conscious Computations, IACR ePrint'22](https://eprint.iacr.org/2022/675)\r\n* [LLAMA: A Low Latency Math Library for Secure Inference, PoPETs'22](https://eprint.iacr.org/2022/793)\r\n* [Pika: Secure Computation using Function Secret Sharing over Rings, PoPETs'22](https://eprint.iacr.org/2022/826)\r\n* [Piranha: A GPU Platform for Secure Computation, USENIX Security'22](https://www.usenix.org/conference/usenixsecurity22/presentation/watson)\r\n* [Efficient Secure Three-Party Sorting with Applications to Data Analysis and Heavy Hitters, CCS'22](https://eprint.iacr.org/2019/695)\r\n* [Private and Reliable Neural Network Inference, CCS'22](https://files.sri.inf.ethz.ch/website/papers/ccs22-phoenix.pdf)\r\n* [SortingHat: Efficient Private Decision Tree Evaluation via Homomorphic Encryption and Transciphering, CCS'22](https://eprint.iacr.org/2022/757)\r\n* [Iron: Private Inference on Transformers, NeurIPS '22](https://openreview.net/forum?id=deyqjpcTfsG)\r\n* [Private and Reliable Neural Network Inference, CCS'22](https://files.sri.inf.ethz.ch/website/papers/ccs22-phoenix.pdf)\r\n* [SecureBiNN: 3-Party Secure Computation for Binarized Neural Network Inference, ESORICS'22](https://link.springer.com/chapter/10.1007/978-3-031-17143-7_14)\r\n* [Meteor: Improved Secure 3-Party Neural Network Inference with Reducing Online Communication Costs, WWW'23](https://dl.acm.org/doi/abs/10.1145/3543507.3583272)\r\n* [Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy, S\u0026P'23](https://www.computer.org/csdl/proceedings-article/sp/2023/933600a076/1He7XMLcnsc)\r\n* [Bicoptor: Two-round Secure Three-party Non-linear Computation without Preprocessing for Privacy-preserving Machine Learning, S\u0026P'23](https://www.computer.org/csdl/proceedings-article/sp/2023/933600b295/1Js0DPq2AqQ)\r\n* [Fusion: Efficient and Secure Inference Resilient to Malicious Servers, NDSS'23](https://www.ndss-symposium.org/ndss-paper/fusion-efficient-and-secure-inference-resilient-to-malicious-servers/)\r\n* [REDsec: Running Encrypted Discretized Neural Networks in Seconds, NDSS'23](https://www.ndss-symposium.org/ndss-paper/redsec-running-encrypted-discretized-neural-networks-in-seconds/)\r\n* [SoK: Cryptographic Neural-Network Computation, S\u0026P'23](https://sokcryptonn.github.io/)\r\n* [Secure Floating-Point Training, USENIX Security'23](https://www.usenix.org/system/files/sec23fall-prepub-212-rathee.pdf)\r\n* [Squirrel: A Scalable Secure Two-Party Computation Framework for Training Gradient Boosting Decision Tree, USENIX Security'23](https://www.usenix.org/conference/usenixsecurity23/presentation/lu)\r\n* [Efficient 3PC for Binary Circuits with Application to Maliciously-Secure DNN Inference, USENIX Security'23](https://www.usenix.org/biblio-13767)\r\n* [Level Up: Private Non-Interactive Decision Tree Evaluation using Levelled Homomorphic Encryption, CCS'23](https://cs.paperswithcode.com/paper/level-up-private-non-interactive-decision)\r\n* [PUMA: Secure Inference of LLaMA-7B in Five Minutes](https://arxiv.org/abs/2307.12533)\r\n* [Orca: FSS-based Secure Training and Inference with GPUs, S\u0026P'24](https://www.computer.org/csdl/proceedings-article/sp/2024/313000a063/1RjEaAAmAAE)\r\n* [SIGMA: Secure GPT Inference with Function Secret Sharing](https://www.microsoft.com/en-us/research/publication/sigma-secure-gpt-inference-with-function-secret-sharing/)\r\n* [CipherGPT: Secure Two-Party GPT Inference](https://eprint.iacr.org/2023/1147)\r\n* [HELiKs: HE Linear Algebra Kernels for Secure Inference, CCS'23](https://dl.acm.org/doi/10.1145/3576915.3623136)\r\n* [MPCDIFF: Testing and Repairing MPC-Hardened Deep Learning Models, NDSS'24](https://www.ndss-symposium.org/ndss-paper/mpcdiff-testing-and-repairing-mpc-hardened-deep-learning-models/)\r\n* [Securely Training Decision Trees Efficiently, CCS'2024](https://eprint.iacr.org/2024/1077)\r\n* [Ents: An Efficient Three-party Training Framework for Decision Trees by Communication Optimization, CCS'24](https://arxiv.org/pdf/2406.07948)\r\n* [CoGNN: Towards Secure and Efficient Collaborative Graph Learning, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3670300)\r\n* [Fast and Accurate Homomorphic Softmax Evaluation, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3670369)\r\n* [Graphiti: Secure Graph Computation Made More Scalable, CCS'24](https://eprint.iacr.org/2024/1756)\r\n* [Rhombus: Fast Homomorphic Matrix-Vector Multiplication for Secure Two-Party Inference, CCS'24](https://eprint.iacr.org/2024/1611)\r\n* [NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3690375)\r\n* [Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions, CCS'24](https://www.usenix.org/system/files/usenixsecurity24-diaa.pdf)\r\n* [MD-ML: Super Fast Privacy-Preserving Machine Learning for Malicious Security with a Dishonest Majority, USENIX Security'24](https://www.usenix.org/conference/usenixsecurity24/presentation/yuan)\r\n* [Accelerating Secure Collaborative Machine Learning with Protocol-Aware RDMA, USENIX Security'24](https://www.usenix.org/conference/usenixsecurity24/presentation/ren)\r\n\r\n# MPC\r\n* [实用安全多方计算协议关键技术研究进展, 计算机研究与发展'15](https://crad.ict.ac.cn/CN/10.7544/issn1000-1239.2015.20150763)\r\n* [Scalable and unconditionally secure multiparty computation, Crypto'07](https://www.iacr.org/archive/crypto2007/46220565/46220565.pdf)\r\n* [Sharemind: A framework for fast privacy-preserving computations, ESORICS'08](https://link.springer.com/chapter/10.1007/978-3-540-88313-5_13)\r\n* [Secure computation with fixed-point numbers, FC'10](https://link.springer.com/chapter/10.1007/978-3-642-14577-3_6)\r\n* [Multiparty computation from somewhat homomorphic encryption, Crypto'12](https://link.springer.com/chapter/10.1007/978-3-642-32009-5_38)\r\n* [Practical covertly secure MPC for dishonest majority–or: breaking the SPDZ limits, ESORICS'13](https://link.springer.com/chapter/10.1007/978-3-642-40203-6_1)\r\n* [GMW vs. Yao? Efficient secure two-party computation with low depth circuits, FC'13](https://link.springer.com/chapter/10.1007/978-3-642-39884-1_23)\r\n* [Efficiently Verifiable Computation on Encrypted Data, CCS'14](https://dl.acm.org/citation.cfm?id=2660366)\r\n* [ABY: A Framework for Efficient Mixed-Protocol Secure Two-Party Computation, NDSS'15](https://encrypto.de/papers/DSZ15.pdf)\r\n* [MASCOT: faster malicious arithmetic secure computation with oblivious transfer, CCS'16](https://dl.acm.org/citation.cfm?id=2978357)\r\n* [High-Throughput Semi-Honest Secure Three-Party Computation with an Honest Majority, CCS'16](https://dl.acm.org/citation.cfm?id=2978331)\r\n* [High- throughput secure three-party computation for malicious adversaries and an honest majority, Crypto'17](https://eprint.iacr.org/2016/944.pdf)\r\n* [A Framework for Constructing Fast MPC over Arithmetic Circuits with Malicious Adversaries and an Honest-Majority, CCS'17](https://eprint.iacr.org/2017/816.pdf)\r\n* [Overdrive^2k: Making SPDZ Great Again, Eurocrypto'18](https://eprint.iacr.org/2017/1230)\r\n* [SPDZ^2k: Efficient MPC mod 2^k for Dishonest Majority, Crypto'18](https://link.springer.com/chapter/10.1007/978-3-319-96881-0_26)\r\n* [Secure outsourced matrix computation and application to neural networks, CCS'18](https://dl.acm.org/doi/10.1145/3243734.3243837)\r\n* [Fast large-scale honest-majority MPC for malicious adversaries, Crypto'18](https://eprint.iacr.org/2018/570)\r\n* [Minimising communication in honest-majority MPC by batchwise multiplication verification, ACNS'18](https://eprint.iacr.org/2018/474)\r\n* [PrivPy: General and Scalable Privacy-Preserving Data Mining, KDD'19](https://dl.acm.org/doi/abs/10.1145/3292500.3330920)\r\n* [Two-thirds honest-majority MPC for malicious adversaries at almost the cost of semi-honest, CCS'19](https://dl.acm.org/doi/10.1145/3319535.3339811)\r\n* [Turbospeedz: Double your online SPDZ! Improving SPDZ using function dependent preprocessing, ACNS'19](https://eprint.iacr.org/2019/080)\r\n* [MP-SPDZ: A Versatile Framework for Multi-Party Computation, CCS'20](https://dl.acm.org/doi/10.1145/3372297.3417872)\r\n* [Senate: A Maliciously-Secure MPC Platform for Collaborative Analytics, USENIX Security'20](https://www.usenix.org/conference/usenixsecurity21/presentation/poddar)\r\n* [Improved primitives for mpc over mixed arithmetic-binary circuits, CRYPTO'20](https://eprint.iacr.org/2020/338.pdf)\r\n* [Malicious Security Comes Free in Honest-Majority MPC, ePrint'20](https://eprint.iacr.org/2020/134)\r\n* [MOTION - A Framework for Mixed-Protocol Multi-Party Computation, TOPS'21](https://eprint.iacr.org/2020/1137)\r\n* [ABY2.0: Improved Mixed-Protocol Secure Two-Party Computation (Full Version), USENIX Security'21](https://eprint.iacr.org/2020/1225.pdf)\r\n* [SynCirc: Efficient Synthesis of Depth-Optimized Circuits for Secure Computation, HOST'21](https://encrypto.de/papers/PSSY21HOST.pdf)\r\n* [MAGE: Nearly Zero-Cost Virtual Memory for Secure Computation, USENIX OSDI'21](https://www.usenix.org/conference/osdi21/presentation/kumar)\r\n* [VASA : Vector AES Instructions for Security Applications, ACSAC'21](https://eprint.iacr.org/2021/1493.pdf)\r\n* [ATLAS: Efficient and Scalable MPC in the Honest Majority Setting, CRYPTO'21](https://eprint.iacr.org/2021/833)\r\n* [The Cost of IEEE Arithmetic in Secure Computation, LatinCrypt'21](https://eprint.iacr.org/2021/054)\r\n* [Fast Fully Secure Multi-Party Computation over Any Ring with Two-Thirds Honest Majority, CCS'22](https://eprint.iacr.org/2022/623)\r\n* [NFGen: Automatic Non-linear Function Evaluation Code Generator for General-purpose MPC Platforms, CCS'22](https://www.sigsac.org/ccs/CCS2022/program/accepted-papers.html)\r\n* [PentaGOD: Stepping beyond Traditional GOD with Five Parties, CCS'22](https://eprint.iacr.org/2022/1118)\r\n* [TurboPack: Honest Majority MPC with Constant Online Communication, CCS'22](https://www.sigsac.org/ccs/CCS2022/program/accepted-papers.html)\r\n* [Selective MPC: Distributed Computation of Differentially Private Key-Value Statistics, CCS'22](https://arxiv.org/abs/2107.12407)\r\n* [To Trust or Not to Trust: Hybrid Multi-party Computation with Trusted Execution Environment, NDSS'22](https://www.ndss-symposium.org/ndss-paper/auto-draft-222/)\r\n* [Binary Search in Secure Computation, NDSS'22](https://eprint.iacr.org/2021/1049)\r\n* [More Efficient Dishonest Majority Secure Computation over $\\mathbb{Z}_{2^k}$ via Galois Rings, Crypto'22](https://eprint.iacr.org/2022/815)\r\n* [Sharing Transformation and Dishonest Majority MPC with Packed Secret Sharing, Crypto'22](https://eprint.iacr.org/2022/831)\r\n* [Le Mans: Dynamic and Fluid MPC for Dishonest Majority, Crypto'22](https://eprint.iacr.org/2021/1579)\r\n* [Round-Optimal and Communication-Efficient Multiparty Computation, EUROCRYPT'22](https://eprint.iacr.org/2020/1437)\r\n* [Practical Non-interactive Publicly Verifiable Secret Sharing with Thousands of Parties, EUROCRYPT'22](https://eprint.iacr.org/2021/1397)\r\n* [Highly Efficient OT-Based Multiplication Protocols, EUROCRYPT'22](https://eprint.iacr.org/2021/1373.pdf)\r\n* [Batch-OT with Optimal Rate, EUROCRYPT'22](https://www.iacr.org/cryptodb/data/paper.php?pubkey=31828)\r\n* [Round-Optimal Multi-Party Computation with Identifiable Abort, EUROCRYPT'22](https://eprint.iacr.org/2022/645)\r\n* [Secure Multiparty Computation with Free Branching, EUROCRYPT'22](https://www.iacr.org/cryptodb/data/paper.php?pubkey=31942)\r\n* [Secure Multiparty Computation with Sublinear Preprocessing, EUROCRYPT'22](https://iacr.org/cryptodb/data/paper.php?pubkey=31948)\r\n* [Attaining GOD Beyond Honest Majority With Friends and Foes, Asiacrypt'22](https://eprint.iacr.org/2022/1207)\r\n* [Polymath: Low-Latency MPC via Secure Polynomial Evaluations and Its Applications, PoPETs'22](https://petsymposium.org/popets/2022/popets-2022-0020.pdf)\r\n* [Silph: A Framework for Scalable and Accurate Generation of Hybrid MPC Protocols, S\u0026P'23](https://www.computer.org/csdl/proceedings-article/sp/2023/933600b796/1Js0Em52Wn6)\r\n* [Faster Secure Comparisons with Offline Phase for Efficient Private Set Intersection, NDSS'23](https://www.ndss-symposium.org/ndss-paper/faster-secure-comparisons-with-offline-phase-for-efficient-private-set-intersection/)\r\n* [FLUTE: Fast and Secure Lookup Table Evaluations, S\u0026P'23](https://eprint.iacr.org/2023/499)\r\n* [Linear Communication in Malicious Majority MPC, CCS'23](https://eprint.iacr.org/2022/781)\r\n* [Ruffle: Rapid 3-party shuffle protocols, PoPETs'23](https://eprint.iacr.org/2023/431)\r\n* [Grotto: Screaming fast (2+1)-PC or $\\mathbb{Z}_{2^n}$ via (2,2)-DPFs, CCS'23](https://eprint.iacr.org/2023/108)\r\n* [COMBINE: COMpilation and Backend-INdependent vEctorization for Multi-Party Computation, CCS'23](https://dl.acm.org/doi/abs/10.1145/3576915.3623181)\r\n* [Don’t Eject the Impostor: Fast Three-Party Computation With a Known Cheater, S\u0026P'24](https://eprint.iacr.org/2023/1744)\r\n* [Scalable Mixed-Mode MPC, IEEE S\u0026P'24](https://eprint.iacr.org/2023/1700)\r\n* [Efficient Secret Sharing for Large-Scale Applications, CCS'24](https://eprint.iacr.org/2024/1045)\r\n* [Secure Multiparty Computation with Lazy Sharing, CCS'24](https://eprint.iacr.org/2024/1347)\r\n* [Coral: Maliciously Secure Computation Framework for Packed and Mixed Circuits, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3690223)\r\n* [Sublinear Distributed Product Checks on Replicated Secret-Shared Data over Z2𝑘 without Ring Extensions, CCS'24](https://eprint.iacr.org/2024/700.pdf)\r\n* [PINE: Efficient Verification of a Euclidean Norm Bound of a Secret-Shared Vector, USENIX Security'24](https://www.usenix.org/conference/usenixsecurity24/presentation/rothblum)\r\n\r\n\r\n# Zero Knowledge for Machine Learning\r\n* [Mystique: Efficient Conversions for Zero-Knowledge Proofs with Applications to Machine Learning, USENIX Security'21](https://eprint.iacr.org/2021/730)\r\n* [ZEN: Efficient Zero-Knowledge Proofs for Neural Networks](https://eprint.iacr.org/2021/087/20210127:132648)\r\n* [zkCNN: Zero Knowledge Proofs for Convolutional Neural Network Predictions and Accuracy, CCS'21](https://eprint.iacr.org/2021/673)\r\n* [Zero-Knowledge Proofs of Training for Deep Neural Networks, CCS'24](https://eprint.iacr.org/2024/162)\r\n* [zkLLM: Zero Knowledge Proofs for Large Language Models, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3670334)\r\n* [Sparrow : Space-Efficient zkSNARK for Data-Parallel Circuits and Applications to Zero-Knowledge Decision Trees, CCS'24](https://eprint.iacr.org/2024/1631)\r\n* [Scalable Zero-knowledge Proofs for Non-linear Functions in Machine Learning, USENIX Security'24](https://www.usenix.org/conference/usenixsecurity24/presentation/hao-meng-scalable)\r\n\r\n\r\n# Federated Learning\r\n## Secure Federated Learning\r\n* [Privacy-Preserving Deep Learning, CCS'15](https://dl.acm.org/citation.cfm?id=2813687)\r\n* [Prio: Private, Robust, and Scalable Computation of Aggregate Statistics, NSDI'17](https://www.usenix.org/conference/nsdi17/technical-sessions/presentation/corrigan-gibbs)\r\n* [Practical Secure Aggregation for Privacy Preserving Machine Learning, CCS'17](https://eprint.iacr.org/2017/281.pdf)\r\n* [Privacy-Preserving Deep Learning via Additively Homomorphic Encryption, TIFS'17](https://ieeexplore.ieee.org/document/8241854)\r\n* [NIKE-based Fast Privacy-preserving High-dimensional Data Aggregation for Mobile Devices, CACR'18](http://cacr.uwaterloo.ca/techreports/2018/cacr2018-10.pdf)\r\n* [PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks, CCSW'19](https://eprint.iacr.org/2019/979.pdf)\r\n* [VerifyNet: Secure and verifiable federated learning, TIFS'19](https://ieeexplore.ieee.org/abstract/document/8765347)\r\n* [PrivColl: Practical Privacy-Preserving Collaborative Machine Learning](https://link.springer.com/chapter/10.1007/978-3-030-58951-6_20)\r\n* [NPMML: A Framework for Non-interactive Privacy-preserving Multi-party Machine Learning, TDSC'20](https://ieeexplore.ieee.org/abstract/document/8981947)\r\n* [SAFER: Sparse secure Aggregation for FEderated leaRning](https://arxiv.org/abs/2007.14861)\r\n* [Secure Byzantine-Robust Machine Learning](https://arxiv.org/abs/2006.04747)\r\n* [Secure Single-Server Aggregation with (Poly)Logarithmic Overhead, CCS'20](https://eprint.iacr.org/2020/704.pdf)\r\n* [Batchcrypt: Efficient homomorphic encryption for cross-silo federated learning, USENIX ATC'21](https://www.usenix.org/conference/atc20/presentation/zhang-chengliang)\r\n* [FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection, DASFAA'20](https://arxiv.org/abs/2003.10637)\r\n* [FLGUARD: Secure and Private Federated Learning, Cryptology Eprint'21](https://eprint.iacr.org/2021/025)\r\n* [Biscotti: A Blockchain System for Private and Secure Federated Learning, TPDS'21](https://ieeexplore.ieee.org/document/9292450)\r\n* [POSEIDON: Privacy-Preserving Federated Neural Network Learning, NDSS'21](https://arxiv.org/abs/2009.00349)\r\n* [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments, MobiSys'21](https://arxiv.org/abs/2104.14380)\r\n* [EIFFeL: Ensuring Integrity for Federated Learning, CCS'22](https://arxiv.org/abs/2112.12727)\r\n* [Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors, USENIX Security'22](https://www.usenix.org/conference/usenixsecurity22/presentation/stevens)\r\n* [Prio+: Privacy Preserving Aggregate Statistics via Boolean Shares, SCN'22](https://link.springer.com/chapter/10.1007/978-3-031-14791-3_23)\r\n* [Local and Central Differential Privacy for Robustness and Privacy in Federated Learning, NDSS'22](https://arxiv.org/abs/2009.03561)\r\n* [ELSA: Secure Aggregation for Federated Learning with Malicious Actors, S\u0026P'23](https://eprint.iacr.org/2022/1695)\r\n* [Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning, SP'23](https://eprint.iacr.org/2023/486)\r\n* [RoFL: Robustness of Secure Federated Learning, SP'23](https://arxiv.org/abs/2107.03311)\r\n* [Two-Tier Data Packing in RLWE-based Homomorphic Encryption for Secure Federated Learning, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3690191)\r\n\r\n## Communication Optimization\r\n* [Terngrad: Ternary gradients to reduce communication in distributed deep learning, NIPS'17](http://papers.nips.cc/paper/6749-terngrad-ternary-gradients-to-reduce-communication-in-distributed-deep-learning)\r\n* [The Convergence of Sparsified Gradient Methods, NIPS'18](https://papers.nips.cc/paper/2018/hash/314450613369e0ee72d0da7f6fee773c-Abstract.html)\r\n\r\n## Byzantine-Tolerant\r\n* [Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent, NIPS'17](http://papers.nips.cc/paper/6617-machine-learning-with-adversaries-byzantine-tolerant-gradient-descent)\r\n* [Byzantine stochastic gradient descent, NIPS'18](https://papers.nips.cc/paper/2018/file/a07c2f3b3b907aaf8436a26c6d77f0a2-Paper.pdf)\r\n* [The Hidden Vulnerability of Distributed Learning in Byzantium, ICML'18](https://arxiv.org/abs/1802.07927)\r\n* [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates, ICML'18](https://arxiv.org/abs/1803.01498)\r\n* [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning, USENIX Security'20](https://www.usenix.org/conference/usenixsecurity20/presentation/fang)\r\n* [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping, NDSS'21](https://arxiv.org/abs/2012.13995)\r\n* [Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses for Federated Learning, NDSS'21](https://www.ndss-symposium.org/ndss-paper/manipulating-the-byzantine-optimizing-model-poisoning-attacks-and-defenses-for-federated-learning/)\r\n* [Justinian’s GAAvernor: Robust Distributed Learning with Gradient Aggregation Agent, USENIX Security'20](https://www.usenix.org/system/files/sec20-pan.pdf)\r\n* [Byzantine-robust and privacy-preserving framework for FEDML, ICLR Workshop'21](https://arxiv.org/pdf/2105.02295.pdf)\r\n* [Learning from History for Byzantine Robust Optimization, ICML'21](http://proceedings.mlr.press/v139/karimireddy21a/karimireddy21a.pdf)\r\n* [FLAME: Taming backdoors in federated learning, USENIX Security'22](https://arxiv.org/abs/2101.02281)\r\n* [BayBFed: Bayesian Backdoor Defense for Federated Learning, SP'23](https://arxiv.org/abs/2301.09508)\r\n* [Byzantine-Robust Decentralized Federated Learning, CCS'24](https://dl.acm.org/doi/10.1145/3658644.3670307)\r\n\r\n\r\n# Privacy Leakages of ML/FL\r\n* [Membership inference attacks against machine learning models, S\u0026P'17](https://ieeexplore.ieee.org/abstract/document/7958568)\r\n* [Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning, S\u0026P'19](https://ieeexplore.ieee.org/abstract/document/8835245)\r\n* [Data Poisoning Attacks Against Federated Learning Systems, ESORICS'20](https://link.springer.com/chapter/10.1007/978-3-030-58951-6_24)\r\n* [A Framework for Evaluating Client Privacy Leakages in Federated Learning, ESORICS'20](https://link.springer.com/chapter/10.1007/978-3-030-58951-6_27)\r\n* [A Critical Overview of Privacy in Machine Learning, IEEE Security \u0026 Privacy'21](https://www.computer.org/csdl/magazine/sp/2021/04/09433648/1tHMTWXyaUE)\r\n* [Enhanced Membership Inference Attacks against Machine Learning Models, CCS'22](https://arxiv.org/abs/2111.09679)\r\n\r\n\r\n# Blogs\r\n* [Cryptography and Machine Learning: Mixing both for private data analysis](https://mortendahl.github.io/)\r\n* [Building Safe A.I.: A Tutorial for Encrypted Deep Learning](https://iamtrask.github.io/2017/03/17/safe-ai/)\r\n* [Awesome MPC: Curated List of resources for MPC](https://github.com/rdragos/awesome-mpc)\r\n* [机器学习隐私保护](https://www.zhihu.com/column/c_1121838720017338368)\r\n\r\n\r\n# Libraries and Frameworks\r\n* [TinyGarble: Logic Synthesis and Sequential Descriptions for Yao's Garbled Circuits](https://github.com/esonghori/TinyGarble)\r\n* [SPDZ-2: Multiparty computation with SPDZ, MASCOT, and Overdrive offline phases](https://github.com/bristolcrypto/SPDZ-2)\r\n* [ABY: A Framework for Efficient Mixed-Protocol Secure Two-Party Computation](https://github.com/encryptogroup/aby)\r\n* [Obliv - C: C compiler for embedding privacy preserving protocols:](http://oblivc.org/)\r\n* [TFHE: Fast Fully Homomorphic Encryption Library over the Torus](https://github.com/tfhe/tfhe)\r\n* [SEAL: Simple Encypted Arithmatic Library](https://www.microsoft.com/en-us/research/project/simple-encrypted-arithmetic-library/)\r\n* [PySEAL: Python interface to SEAL](https://github.com/Lab41/PySEAL)\r\n* [HElib: An Implementation of homomorphic encryption](https://github.com/shaih/HElib])\r\n* [EzPC: programmable, efficient, and scalable secure two-party computation for machine learning](https://github.com/mpc-msri/EzPC)\r\n* [CUDA-accelerated Fully Homomorphic Encryption Library](https://github.com/vernamlab/cuFHE)\r\n* [CrypTen: A framework for Privacy Preserving Machine Learning](https://github.com/facebookresearch/CrypTen)\r\n* [tf-encrypted: A Framework for Machine Learning on Encrypted Data](https://github.com/tf-encrypted/tf-encrypted)\r\n* [Sharemind](https://sourceforge.net/projects/sharemind/)\r\n* [PythonPaillier](https://github.com/data61/python-paillier)\r\n* [TenSEAL](https://github.com/OpenMined/TenSEAL)\r\n* [MP-SPDZ](https://github.com/data61/MP-SPDZ)\r\n* [Securenn-public](https://github.com/snwagh/securenn-public)\r\n* [SecMML](https://github.com/FudanMPL/SecMML)\r\n* [mnist-mpc](https://github.com/csiro-mlai/mnist-mpc)\r\n* [Private-Set-Intersection](https://github.com/bit-ml/Private-Set-Intersection)\r\n* [falcon-public](https://github.com/snwagh/falcon-public)\r\n* [Rosetta](https://github.com/LatticeX-Foundation/Rosetta)\r\n* [Antchain-MPC](https://github.com/alipay/Antchain-MPC)\r\n* [Kunlun](https://github.com/yuchen1024/Kunlun)\r\n* [MOTION2NX](https://github.com/encryptogroup/MOTION2NX)\r\n* [SecureQ8](https://github.com/anderspkd/SecureQ8)\r\n* [mpc-benchmarks](https://github.com/mkskeller/mpc-benchmarks)\r\n* [muse](https://github.com/mc2-project/muse)\r\n* [Primihub](https://github.com/primihub/primihub)\r\n* [concrete](https://github.com/zama-ai/concrete)\r\n* [SecretFlow](https://github.com/secretflow/secretflow)\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYe-D%2FPPML-Resource","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FYe-D%2FPPML-Resource","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FYe-D%2FPPML-Resource/lists"}