A Survey: Computing Models of Artificial Intelligence Privacy Protection Based on Cryptographic Techniques

被引：0
作者：
Tian H.-B. [1 ]
Liang X.-Q. [1 ]
机构：
[1] School of Computer Science and Engineering, Sun Yat-Sen University, Guangdong, Guangzhou
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2023年 / 51卷 / 08期
关键词：
algorithms; artificial intelligence; computation models; cryptographic techniques; privacy protection; protocols;
D O I：
10.12263/DZXB.20210702
中图分类号：
学科分类号：
摘要：
The application scenarios of artificial intelligence privacy protection are diverse. In different scenarios, the trustness and number of entities fulfilling privacy protection computation are different. The trustness and number of these entities have an important impact on the technical choices of privacy protection computation. Starting from the trustness and number of entities, this paper classifies the computation methods of artificial intelligence privacy protection, which are based on cryptographic techniques into four types of computation models: multiple centers model, double centers model, single center model and real model. Except for the real model, there are trusted entities in all other computation models. For each kind of computation model, this paper presents the typical computations and algorithms, which are involved in the current artificial intelligence privacy protection methods based on cryptography tools. And this paper also points out that improving the efficiency and security of algorithms is an applicable research direction for each model. © 2023 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：2260 / 2276
页数：16
相关论文
共 66 条
  • [1] DOWLIN N, GILAD-BACHRACH R, LAINE K, Et al., Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy, Proceedings of the 33rd International Conference on International Conference on Machine Learning, pp. 19-24, (2016)
  • [2] WU Y, CAI S, XIAO X, Et al., Privacy preserving vertical federated learning for tree-based models, VLDB Endow⁃ ment, 13, 11, pp. 2090-2103, (2020)
  • [3] YAO A C., Protocols for secure computations, Proceed⁃ ings of the 23rd Annual Symposium on Foundations of Computer Science, pp. 160-164, (1982)
  • [4] GOLDREICH O, MICALI S, WIGDERSON A., How to play any mental game, Proceedings of the Nineteenth Annual ACM Symposium on Theory of Computing, pp. 218-229, (1987)
  • [5] DAVID E, VLADIMIR K, MIKE R., A pragmatic introduc⁃ tion to secure multi-party computation, Foundations and Trends in Privacy and Security, 2, 2-3, pp. 70-246, (2018)
  • [6] JI S L, DU T Y, LI J F, Et al., Security and pdvacy of ma⁃ chine learning models: A survey, Journal of Software, 32, 1, pp. 41-67, (2021)
  • [7] TAN Z W, ZHANG L F., Survey on privacy preserving techniques for machine learning, Journal of Software, 31, 7, pp. 2127-2156, (2020)
  • [8] LIU R X, CHEN H, GUO R Y, Et al., Survey on privacy at⁃ tacks and defenses in machine learning, Joumal of Soft⁃ ware, 31, 3, pp. 866-892, (2020)
  • [9] AL-RUBAIE M, CHANG J M., Privacy-preserving ma⁃ chine learning: Threats and solutions, IEEE Security Pri⁃ vacy, 17, 2, pp. 49-58, (2019)
  • [10] TANUWIDJAJA H C, CHOI R, KIM K., A survey on deep learning techniques for privacy-preserving, Pro⁃ ceedings of the Second International Conference on Ma⁃ chine Learning for Cyber Security, pp. 29-46, (2019)
1234567