一、密码算法的应用

1.联邦学习

1.1. 横向联邦

[PAHWM18] Le Trieu Phong, Yoshinori Aono, Takuya Hayashi, Lihua Wang, Shiho Moriai: Privacy-Preserving Deep Learning via Additively Homomorphic Encryption. IEEE Trans. Inf. Forensics Secur. 13(5): 1333-1345 (2018)

1.2. 纵向联邦

[YRZL] Shengwen Yang, Bing Ren, Xuhui Zhou, Liping Liu: Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator. CoRR abs/1911.09824 (2019) 

[HHINPST17] Stephen Hardy, Wilko Henecka, Hamish Ivey-Law, Richard Nock, Giorgio Patrini, Guillaume Smith, Brian Thorne:
Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. CoRR abs/1711.10677 (2017)

2.同态与应用

2.1. 同态应用于AI训练

Only加法同态

[AHPW16a] Y. Aono, T. Hayashi, L. T. Phong, and L. Wang. Privacy-preserving logistic regression with distributed data sources via homomorphic encryption. IEICE Transactions, 99-D(8):2079–2089, 2016. 

[AHPW16b] Y. Aono, T. Hayashi, L. T. Phong, and L. Wang. Scalable and secure logistic regression via homomorphic encryption. In Proceedings of the Sixth ACM on Conference on Data and Application Security and Privacy, CODASPY, pages 142–144, 2016.

2.2. 同态应用于AI推理

[GDLLNW16] Ran Gilad-Bachrach, Nathan Dowlin, Kim Laine, Kristin E. Lauter, Michael Naehrig, John Wernsing:CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy. ICML 2016: 201-210

[Rah22] Yogachandran Rahulamathavan:
Privacy-preserving Similarity Calculation of Speaker Features Using Fully Homomorphic Encryption. CoRR abs/2202.07994 (2022).

贡献：使用全同态来保护用户声纹信息

 3. MPC与应用

3.1. MPC应用于AI训练

[MZ17] ayman Mohassel, Yupeng Zhang: SecureML: A System for Scalable Privacy-Preserving Machine Learning. IEEE Symposium on Security and Privacy 2017: 19-38

3.2. MPC应用于AI推理

[HLHD22] Zhicong Huang, Wen-jie Lu, Cheng Hong,Jiansheng Ding. Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference. 

[RRKCGRS20] Deevashwer Rathee, Mayank Rathee, Nishant Kumar, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma: CrypTFlow2: Practical 2-Party Secure Inference. CCS 2020: 325-342

[MLSZP20] Pratyush Mishra, Ryan Lehmkuhl, Akshayaram Srinivasan, Wenting Zheng, Raluca Ada Popa: Delphi: A Cryptographic Inference Service for Neural Networks. USENIX Security Symposium 2020: 2505-2522

[JVP18] Chiraag Juvekar, Vinod Vaikuntanathan, Anantha P. Chandrakasan: GAZELLE: A Low Latency Framework for Secure Neural Network Inference. USENIX Security Symposium 2018: 1651-1669

 

4.隐私集合求交--PSI(Private Set Intersection)

4.1 综述

[CLYCZW2019] 崔泓睿,刘天怡, 郁昱, 程越强, 张煜龙, 韦韬. 多方安全计算热点：隐私保护集合求交技术 (PSI) 分析研究报告

4.2 基于公钥加密体系的PSI

4.2.1 基于全同态

[CLR17] Hao Chen, Kim Laine, Peter Rindal: Fast Private Set Intersection from Homomorphic Encryption. CCS 2017: 1243-1255

[CHLR18] Hao Chen, Zhicong Huang, Kim Laine, and Peter Rindal. Labeled PSI from Fully Homomorphic Encryption with Malicious Security. CCS2018:1223-1237.

[CMGDILR21] Kelong Cong, Radames Cruz Moreno, Mariana Botelho da Gama, Wei Dai, Ilia Iliashenko, Kim Laine, Michael Rosenberg: Labeled PSI from Homomorphic Encryption with Reduced Computation and Communication. CCS 2021: 1135-1150

4.2.2 基于非全同态

[RA18] Amanda Cristina Davi Resende, Diego F. Aranha:Faster Unbalanced Private Set Intersection. Financial Cryptography 2018: 203-221

4.3 基于OT

[CM20] Melissa Chase, Peihan Miao:Private Set Intersection in the Internet Setting from Lightweight Oblivious PRF. CRYPTO (3) 2020: 34-63

[DCW13] Changyu Dong, Liqun Chen, and Zikai Wen. When private set intersection meets big data: an efficient and scalable protocol. In Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security, pages 789–800. ACM, 2013.

5.隐私语音转录系统

[PRRS13] Manas A. Pathak, Bhiksha Raj, Shantanu Rane, Paris Smaragdis:
Privacy-Preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise. IEEE Signal Process. Mag. 30(2): 62-74 (2013)

[ACFR20] Shimaa Ahmed, Amrita Roy Chowdhury, Kassem Fawaz, Parmesh Ramanathan:
Preech: A System for Privacy-Preserving Speech Transcription. USENIX Security Symposium 2020: 2703-2720

[Rah22] Yogachandran Rahulamathavan:
Privacy-preserving Similarity Calculation of Speaker Features Using Fully Homomorphic Encryption. CoRR abs/2202.07994 (2022)

6.匿踪查询--PIR(Private information retrieval)

6.1 基于全同态

[ACLS18] Sebastian Angel, Hao Chen, Kim Laine, Srinath T. V. Setty:PIR with Compressed Queries and Amortized Query Processing. IEEE Symposium on Security and Privacy 2018: 962-979

二、密码学算法

2.1. 全同态

2.1.1 全同态自举

[BMTH21]Jean-Philippe Bossuat, Christian Mouchet, Juan Ramón Troncoso-Pastoriza, Jean-Pierre Hubaux: Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-sparse Keys. EUROCRYPT (1) 2021: 587-61

[CCS19] Hao Chen, Ilaria Chillotti, and Yongsoo Song. “Improved bootstrapping for approximate homomorphic encryption”. EUROCRYPT 2019, pp. 34–54. 

 

标签：Privacy,Encryption,同态,Homomorphic,Private,隐私,数据安全,文章,Security
来源： https://www.cnblogs.com/dede-0119/p/15963550.html