A Survey on Federated Unlearning: Challenges, Methods, and Future Directions

Author:

Liu Ziyao1ORCID,Jiang Yu2ORCID,Shen Jiyuan2ORCID,Peng Minyi2ORCID,Lam Kwok-Yan1ORCID,Yuan Xingliang3ORCID,Liu Xiaoning4ORCID

Affiliation:

1. Nanyang Technological University, Singapore, Singapore

2. Nanyang Technological University, Singapore Singapore

3. The University of Melbourne, Melbourne, Australia

4. RMIT University, Melbourne, Australia

Abstract

In recent years, the notion of “the right to be forgotten” (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety, requiring the provision of mechanisms that support the removal of personal data of individuals upon their requests. Consequently, machine unlearning (MU) has gained considerable attention which allows an ML model to selectively eliminate identifiable information. Evolving from MU, federated unlearning (FU) has emerged to confront the challenge of data erasure within federated learning (FL) settings, which empowers the FL model to unlearn an FL client or identifiable information pertaining to the client. Nevertheless, the distinctive attributes of federated learning introduce specific challenges for FU techniques. These challenges necessitate a tailored design when developing FU algorithms. While various concepts and numerous federated unlearning schemes exist in this field, the unified workflow and tailored design of FU are not yet well understood. Therefore, this comprehensive survey delves into the techniques and methodologies in FU providing an overview of fundamental concepts and principles, evaluating existing federated unlearning algorithms, and reviewing optimizations tailored to federated learning. Additionally, it discusses practical applications and assesses their limitations. Finally, it outlines promising directions for future research.

Publisher

Association for Computing Machinery (ACM)

Reference159 articles.

1. Manaar Alam Hithem Lamri and Michail Maniatakos. 2023. Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning. arXiv preprint arXiv:2304.10638(2023).

2. Eugene Bagdasaryan and Vitaly Shmatikov. 2021. Blind backdoors in deep learning models. In 30th USENIX Security Symposium (USENIX Security 21). 1505–1521.

3. Hasin Bano, Muhammad Ameen, Muntazir Mehdi, Amaad Hussain, and Pengfei Wang. 2023. Federated Unlearning and Server Right to Forget: Handling Unreliable Client Contributions. In International Conference on Recent Trends in Image Processing and Pattern Recognition. Springer, 393–410.

4. Secure Single-Server Aggregation with (Poly)Logarithmic Overhead

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3