Learn to Unlearn: Insights Into Machine Unlearning

被引：4

作者：

Qu, Youyang ^{[1
]}

Yuan, Xin ^{[1
]}

Ding, Ming ^{[1
]}

Ni, Wei ^{[1
]}

Rakotoarivelo, Thierry ^{[1
]}

Smith, David ^{[1
]}

机构：

[1] Data61, Sydney, NSW, Australia

来源：

COMPUTER | 2024年 / 57卷 / 03期

关键词：

Privacy; Reviews; Machine learning; Resilience; ATTACKS; FORGET;

D O I：

10.1109/MC.2023.3333319

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This article presents a comprehensive review of recent machine unlearning techniques, verification mechanisms, and potential attacks. We highlight emerging challenges and prospective research directions, aiming to provide valuable resources for integrating privacy, equity, and resilience into machine learning systems and help them "learn to unlearn."

引用

页码：79 / 90

页数：12

共 9 条

[1] Bourtoule L, 2021, P IEEE S SECUR PRIV, P141, DOI 10.1109/SP40001.2021.00019
[2] Brophy J., 2021, P 38 INT C MACH LEAR, P1092
[3] Towards Making Systems Forget with Machine Unlearning
Cao, Yinzhi
Yang, Junfeng
[J]. 2015 IEEE SYMPOSIUM ON SECURITY AND PRIVACY SP 2015, 2015, : 463 - 480
[4] When Machine Unlearning Jeopardizes Privacy
Chen, Min
Zhang, Zhikun
Wang, Tianhao
Backes, Michael
Humbert, Mathias
Zhang, Yang
[J]. CCS '21: PROCEEDINGS OF THE 2021 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2021, : 896 - 911
[5] Ginart AA, 2019, ADV NEUR IN, V32
[6] Golatkar A, 2020, PROC CVPR IEEE, P9301, DOI 10.1109/CVPR42600.2020.00932
[7] Marchant NG, 2022, AAAI CONF ARTIF INTE, P7691
[8] Mittal P., 2022, Proceedings on Privacy Enhancing Technologies, V3, P268
[9] Membership Inference Attacks Against Machine Learning Models
Shokri, Reza
Stronati, Marco
Song, Congzheng
Shmatikov, Vitaly
[J]. 2017 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP), 2017, : 3 - 18

← 1 →