Game-theoretical analysis of strategic information transmission for gradient privacy protection

被引：0

作者：

Jiang, Hanyuan ^{[1
,2
]}

Song, Wanjun ^{[2
]}

Bai, Long ^{[2
]}

Li, Yuzhe ^{[1
]}

Chai, Tianyou ^{[1
,3
]}

机构：

[1] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110819, Peoples R China

[2] Guoshen Co, China Energy Grp, Shangyuquan Coal Mine, Hequ, Peoples R China

[3] Northeastern Univ, Natl Engn Technol Res Ctr Met Ind Automat, Shenyang 110819, Peoples R China

来源：

JOURNAL OF CONTROL AND DECISION | 2025年

基金：

中国国家自然科学基金;

关键词：

Machine learning; privacy protection; malicious eavesdropper; game theory;

D O I：

10.1080/23307706.2025.2481910

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Privacy protection of shared gradients in machine learning model training is crucial, yet the coexistence of honest-curious learners and malicious eavesdroppers in the real world is overlooked in research. A linear strategy-based privacy protection method for three-party games with eavesdroppers is proposed to address privacy threats in machine learning model training. Firstly, a three-party game framework is designed based on machine learning model training, with the data owner as the leader and the learner and eavesdropper as followers, leading to a privacy protection optimisation problem. Secondly, two eavesdropping scenarios are considered: limited and complete encoded information. By solving the equilibrium solution of the optimisation problem, the optimal strategy pair is obtained, and a strategic privacy protection information transmission mechanism is proposed. Finally, simulation experiments illustrate the theoretical results, validating the effectiveness of the algorithms proposed in this paper.

引用

页数：14

共 25 条

[1] Deep Learning with Differential Privacy
Abadi, Martin
Chu, Andy
Goodfellow, Ian
McMahan, H. Brendan
Mironov, Ilya
Talwar, Kunal
Zhang, Li
[J]. CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, : 308 - 318
[2] Agarwal N, 2018, Arxiv, DOI arXiv:1805.10559
[3] Information-Theoretic Approach to Strategic Communication as a Hierarchical Game
Akyol, Emrah
Langbort, Cedric
Basar, Tamer
[J]. PROCEEDINGS OF THE IEEE, 2017, 105 (02) : 205 - 218
[4] Alistarh D, 2017, ADV NEUR IN, V30
[5] Bishop N., 2020, Advances in Neural Information Processing Systems, V33, P9520
[6] Bost R., 2014, Machine learning classification over encrypted data
[7] Chen Y, 2024, IEEE T CONTROL NETW, V11, P1825, DOI 10.1109/TCNS.2024.3354886
[8] Dowlin N, 2016, PR MACH LEARN RES, V48
[9] Geiping J., 2020, ADV NEURAL INFORM PR, P16937, DOI DOI 10.5555/3495724.3497145
[10] Graepel Thore, 2013, Information Security and Cryptology - ICISC 2012. 15th International Conference. Revised Selected Papers, P1, DOI 10.1007/978-3-642-37682-5_1

← 1 2 3 →