연합 학습 환경에서의 Task-Specific Adaptive Differential Privacy 메커니즘 평가 방안 연구

우타리예바 아쎔; 최윤호

연합 학습 환경에서의 Task-Specific Adaptive Differential Privacy 메커니즘 평가 방안 연구

우타리예바 아쎔

최윤호

Vol. 34, No. 1, pp. 143-156, 2월. 2024

https://doi.org/10.13089/JKIISC.2024.34.1.143, Full Text:

Keywords: Differential privacy, Federated learning, Adaptive Differential Privacy
Abstract

Federated Learning (FL) has emerged as a potent methodology for decentralized model training across multiple collaborators, eliminating the need for data sharing. Although FL is lauded for its capacity to preserve data privacy, it is not impervious to various types of privacy attacks. Differential Privacy (DP), recognized as the golden standard in privacy-preservation techniques, is widely employed to counteract these vulnerabilities. This paper makes a specific contribution by applying an existing, task-specific adaptive DP mechanism to the FL environment. Our comprehensive analysis evaluates the impact of this mechanism on the performance of a shared global model, with particular attention to varying data distribution and partitioning schemes. This study deepens the understanding of the complex interplay between privacy and utility in FL, providing a validated methodology for securing data without compromising performance.

Statistics

Show / Hide Statistics

Cite this article

[IEEE Style]

우타리예바 아쎔 and 최윤호, "Study on Evaluation Method of Task-Specific Adaptive Differential Privacy Mechanism in Federated Learning Environment," Journal of The Korea Institute of Information Security and Cryptology, vol. 34, no. 1, pp. 143-156, 2024. DOI: https://doi.org/10.13089/JKIISC.2024.34.1.143.

[ACM Style]

우타리예바 아쎔 and 최윤호. 2024. Study on Evaluation Method of Task-Specific Adaptive Differential Privacy Mechanism in Federated Learning Environment. Journal of The Korea Institute of Information Security and Cryptology, 34, 1, (2024), 143-156. DOI: https://doi.org/10.13089/JKIISC.2024.34.1.143.