消除你的痕迹:远程清除联合学习中的后门

Manaar Alam;Hithem Lamri;Michail Maniatakos
{"title":"消除你的痕迹:远程清除联合学习中的后门","authors":"Manaar Alam;Hithem Lamri;Michail Maniatakos","doi":"10.1109/TAI.2024.3465441","DOIUrl":null,"url":null,"abstract":"Federated learning (FL) enables collaborative learning across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and unvetted participants’ data makes it vulnerable to \n<italic>backdoor attacks</i>\n. In these attacks, adversaries selectively inject malicious functionality into the centralized model during training, leading to intentional misclassifications for specific adversary-chosen inputs. While previous research has demonstrated successful injections of persistent backdoors in FL, the persistence also poses a challenge, as their existence in the centralized model can prompt the central aggregation server to take preventive measures for penalizing the adversaries. Therefore, this article proposes a method \n<italic>that enables adversaries to effectively remove backdoors from the centralized model</i>\n upon achieving their objectives or upon suspicion of possible detection. The proposed approach extends the concept of \n<italic>machine unlearning</i>\n and presents strategies to preserve the performance of the centralized model and simultaneously prevent over-unlearning of information unrelated to backdoor patterns, making adversaries stealthy while removing backdoors. To the best of our knowledge, this is the first work exploring machine unlearning in FL to remove backdoors to the benefit of adversaries. Exhaustive evaluation considering various image classification scenarios demonstrates the efficacy of the proposed method for efficient backdoor removal from the centralized model, injected by state-of-the-art attacks across multiple configurations.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6683-6698"},"PeriodicalIF":0.0000,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Get Rid of Your Trail: Remotely Erasing Backdoors in Federated Learning\",\"authors\":\"Manaar Alam;Hithem Lamri;Michail Maniatakos\",\"doi\":\"10.1109/TAI.2024.3465441\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated learning (FL) enables collaborative learning across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and unvetted participants’ data makes it vulnerable to \\n<italic>backdoor attacks</i>\\n. In these attacks, adversaries selectively inject malicious functionality into the centralized model during training, leading to intentional misclassifications for specific adversary-chosen inputs. While previous research has demonstrated successful injections of persistent backdoors in FL, the persistence also poses a challenge, as their existence in the centralized model can prompt the central aggregation server to take preventive measures for penalizing the adversaries. Therefore, this article proposes a method \\n<italic>that enables adversaries to effectively remove backdoors from the centralized model</i>\\n upon achieving their objectives or upon suspicion of possible detection. The proposed approach extends the concept of \\n<italic>machine unlearning</i>\\n and presents strategies to preserve the performance of the centralized model and simultaneously prevent over-unlearning of information unrelated to backdoor patterns, making adversaries stealthy while removing backdoors. To the best of our knowledge, this is the first work exploring machine unlearning in FL to remove backdoors to the benefit of adversaries. Exhaustive evaluation considering various image classification scenarios demonstrates the efficacy of the proposed method for efficient backdoor removal from the centralized model, injected by state-of-the-art attacks across multiple configurations.\",\"PeriodicalId\":73305,\"journal\":{\"name\":\"IEEE transactions on artificial intelligence\",\"volume\":\"5 12\",\"pages\":\"6683-6698\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on artificial intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10685452/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on artificial intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10685452/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

联合学习(FL)可实现多人协作学习,而不会暴露敏感的个人数据。然而,FL 的分布式性质和未经审查的参与者数据使其容易受到后门攻击。在这些攻击中,敌方会在训练过程中选择性地向集中模型注入恶意功能,从而导致对敌方选择的特定输入进行有意的错误分类。虽然之前的研究已经证明在 FL 中成功注入了持久性后门,但这种持久性也带来了挑战,因为它们在集中模型中的存在会促使中央聚合服务器采取预防措施来惩罚对手。因此,本文提出了一种方法,使对手能够在达到目的或怀疑可能被检测到时,有效地从集中模型中删除后门。所提出的方法扩展了机器未学习的概念,并提出了一些策略,以保持集中模型的性能,同时防止过度未学习与后门模式无关的信息,从而使对手在删除后门的同时保持隐秘。据我们所知,这是第一项在 FL 中探索机器非学习以清除后门从而使对手获益的研究。对各种图像分类场景进行的详尽评估表明,所提出的方法能有效地从集中模型中清除后门,并能在多种配置中使用最先进的攻击手段。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Get Rid of Your Trail: Remotely Erasing Backdoors in Federated Learning
Federated learning (FL) enables collaborative learning across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and unvetted participants’ data makes it vulnerable to backdoor attacks . In these attacks, adversaries selectively inject malicious functionality into the centralized model during training, leading to intentional misclassifications for specific adversary-chosen inputs. While previous research has demonstrated successful injections of persistent backdoors in FL, the persistence also poses a challenge, as their existence in the centralized model can prompt the central aggregation server to take preventive measures for penalizing the adversaries. Therefore, this article proposes a method that enables adversaries to effectively remove backdoors from the centralized model upon achieving their objectives or upon suspicion of possible detection. The proposed approach extends the concept of machine unlearning and presents strategies to preserve the performance of the centralized model and simultaneously prevent over-unlearning of information unrelated to backdoor patterns, making adversaries stealthy while removing backdoors. To the best of our knowledge, this is the first work exploring machine unlearning in FL to remove backdoors to the benefit of adversaries. Exhaustive evaluation considering various image classification scenarios demonstrates the efficacy of the proposed method for efficient backdoor removal from the centralized model, injected by state-of-the-art attacks across multiple configurations.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
7.70
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信