КОНФИДЕНЦИАЛЬНОЕ МАШИННОЕ ОБУЧЕНИЕ НА ОСНОВЕ ТРЕХСТОРОННИХ ПРОТОКОЛОВ БЕЗОПАСНЫХ ВЫЧИСЛЕНИЙ
Аннотация
Ключевые слова
Полный текст:
PDFЛитература
1. Evans D., Kolesnikov V., Rosulek M. A pragmatic introduction to secure multi-party computation. – 182 p.
URL: https://securecomputation.org/docs/pragmaticmpc.pdf (дата обращения: 10.01.2022).
2. Запечников С.В., Щербаков А.Ю. Конфиденциальное машинное обучение на основе двусторонних протоколов безопасных вычислений. Безопасность информационных технологий, [S.I.], т. 28, № 4, 2021, с. 39–51.
DOI: http://dx.doi.org/10.26583/bit.2021.4.03.
3. Wagh, S. SecureNN: Efficient and private neural network training. Cryptology ePrint Archive. 2018. – 24 p.
URL: https://eprint.iacr.org/2018/442 (дата обращения: 10.01.2022).
4. Chandran N., Gupta D., Rastogi A., Sharma R., Tripathi S. EzPC: Programmable and Efficient Secure Two-Party Computation for Machine Learning. 2019 IEEE European Symposium on Security and Privacy (EuroS&P), Stockholm, Sweden. 2019, p. 496–511. DOI: http://dx.doi.org/10.1109/EuroSP.2019.00043.
5. Kumar E. et al. CrypTFlow: Secure TensorFlow Inference. arXiv preprint. 2020. – 18 p.
URL: https://arxiv.org/pdf/1909.07814v2.pdf (дата обращения: 10.01.2022).
6. Rathee D. et al. CrypTFlow2: Practical 2-Party Secure Inference. arXiv preprint. 2020. – 18 p.
URL: https://arxiv.org/pdf/2010.06457.pdf (дата обращения: 10.01.2022).
7. Patra A. ABY2.0: Improved mixed-protocol secure two-party computation. A. Patra, T. Schneider,
A. Suresh et al. URL: https://ia.cr/2020/1225 (дата обращения: 10.01.2022).
8. Boemer F. MP2ML: a mixed-protocol machine learning framework for private inference. ARES '20: Proceedings of the 15th International Conference on Availability, Reliability and Security. 2020, p. 1–10.
DOI: http://dx.doi.org/10.1145/3407023.3407045. URL: https://dl.acm.org/doi/abs/10.1145/3407023.3407045 (дата обращения: 10.01.2022)
9. Demmler D. ABY – a framework for efficient mixed-protocol secure two-party computation.
D. Demmler, T. Schneider, M. Zohner. 22nd Network and Distributed System Security Symposium (NDSS'15), Internet Society, San Diego, CA, USA, February 8–11, 2015.
URL: https://encrypto.de/papers/DSZ15.pdf (дата обращения: 10.01.2022).
10. Thien Duc Nguyen, Phillip Rieger, Hossein Yalame, Helen Möllering, Hossein Fereidooni, Samuel Marchal, Markus Miettinen, Azalia Mirhoseini, Ahmad-Reza Sadeghi, Thomas Schneider, and Shaza Zeitouni. FLGUARD: Secure and private federated learning, Jan 6, 2021. URL: https://ia.cr/2021/025 (дата обращения: 10.01.2022).
11. Mishra P. Delphi: A Cryptographic Inference Service for Neural Networks. P. Mishra, R. Lehmkuhl,
A. Srinivasan et al. Proc. of USENIX Security 2020 (USENIX Security Symposium).
URL: https://www.usenix.org/system/files/sec20spring_mishra_prepub.pdf (дата обращения: 10.01.2022).
12. Raluca Ada Popa homepage: Research.
URL: https://people.eecs.berkeley.edu/~raluca/#Research (дата обращения: 10.01.2022).
13. Lehmkuhl R. Muse: Secure Inference Resilient to Malicious Clients.
R. Lehmkuhl, P. Mishra, A. Srinivasan et al. Proc. of USENIX Security 2021 (USENIX Security Symposium). URL: https://people.eecs.berkeley.edu/~raluca/MUSEcamera.pdf (дата обращения: 10.01.2022).
14. Rachuri R. Trident: Efficient 4PC framework for privacy preserving machine learning. Cryptology ePrint Archive. 2019. – 26 p. URL: https://eprint.iacr.org/2019/1315 (дата обращения: 10.01.2022).
15. Byali M. FLASH: Fast and robust framework for privacy-preserving machine. Cryptology ePrint Archive. 2019. – 29 p.
URL: https://eprint.iacr.org/2019/1365 (дата обращения: 10.01.2022).
16. Patra A. BLAZE: Blazing Fast Privacy-Preserving Machine Learning. Cryptology ePrint Archive.
2020. – 28 p. URL: https://eprint.iacr.org/2020/042.pdf (дата обращения: 10.01.2022).
17. Koti N. SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning. Cryptology ePrint Archive.
2020. – 36 p. URL: https://eprint.iacr.org/2020/592.pdf (дата обращения: 10.01.2022).
18. Koti N. Tetrad: Actively Secure 4PC for Secure Training and Inference. Cryptology ePrint Archive.
2021. – 31 p. URL: https://eprint.iacr.org/2021/755.pdf (дата обращения: 10.01.2022).
19. Mohassel P. SecureML: A system for scalable privacy-preserving machine learning. Cryptology ePrint Archive. 2017. – 38 p. URL: https://eprint.iacr.org/2017/396 (дата обращения: 10.01.2022).
20. Mohassel P. ABY3: A mixed protocol framework for machine learning. Cryptology ePrint Archive.
2018. – 40 p. URL: https://eprint.iacr.org/2018/403 (дата обращения: 10.01.2022).
21. Mohassel P. Practical privacy-preserving k-means clustering. Cryptology ePrint Archive. 2019. – 30 p.
URL: https://eprint.iacr.org/2019/1158 (дата обращения: 10.01.2022).
22. Wagh S. Falcon: Honest-Majority Maliciously Secure Framework for Private Deep Learning. Proc. of Privacy Enhancing Technologies Symposium (PETS), June 2021, p. 1–21.
URL: https://arxiv.org/pdf/2004.02229.pdf (дата обращения: 10.01.2022).
23. Sameer W. New directions in efficient privacy-preserving machine learning. Ph. D. Theses. Princeton university. 2020. – 203 p.
URL:https://dataspace.princeton.edu/bitstream/88435/dsp01s7526g34f/1/ Wagh_princeton_0181D_13320.pdf (дата обращения: 10.01.2022).
24. Attrapadung N. Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimation. Cryptology ePrint Archive. 2021. – 24 p.
URL: https://eprint.iacr.org/2021/736.pdf (дата обращения: 10.01.2022).
25. Juvekar C. GAZELLE: A Low Latency Framework for Secure Neural Network Inference. Cryptology ePrint Archive. 2021. – 17 p. URL: https://eprint.iacr.org/2018/073.pdf (дата обращения: 10.01.2022).
26. Liu J. Oblivious Neural Network Predictions via MiniONN transformations. Cryptology ePrint Archive.
2017. – 13 p. URL: https://eprint.iacr.org/2017/452.pdf (дата обращения: 10.01.2022).
27. Ryffel T. AriaNN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing. Preprint.
URL: https://arxiv.org/pdf/2006.04593.pdf (дата обращения: 10.01.2022).
28. Mohassel P. Fast and secure three-party computation: The garbled circuit approach. Cryptology ePrint Archive. 2015. – 18 p. URL: https://eprint.iacr.org/2015/931 (дата обращения: 10.01.2022).
DOI: http://dx.doi.org/10.26583/bit.2022.1.04
Ссылки
- На текущий момент ссылки отсутствуют.
Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.