arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.03233cs.CR
收藏

学习你想要遗忘的内容:针对机器遗忘的遗忘反演攻击

Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning

Hongsheng Hu, Shuo Wang, Tian Dong, Minhui Xue

AI总结:

本文首次研究机器遗忘过程中的隐私泄露风险,提出仅利用原始模型与遗忘后模型恢复被遗忘样本特征和标签的遗忘反演攻击,并评估攻击效果及三类效用代价型防御。

摘要:

机器遗忘已成为实现“被遗忘权”的一种有前景的解决方案,在该权利下,个人可以请求从机器学习模型中删除其数据。然而,现有机器遗忘研究主要关注遗忘方法的有效性和效率,却忽视了对遗忘过程中隐私漏洞的考察。当攻击者能够获得一个模型的两个版本,即原始模型和遗忘后模型时,机器遗忘便开启了一个新的攻击面。在本文中,我们首次开展研究,以理解机器遗忘在多大程度上会泄露被遗忘数据的机密内容。具体而言,在 Machine Learning as a Service(机器学习即服务)设置下,我们提出了遗忘反演攻击,该攻击仅通过访问原始模型和遗忘后模型,就能够揭示被遗忘样本的特征和标签信息。我们通过在基准数据集上、跨多种模型架构,并针对精确和近似两类代表性遗忘方法开展大量实验,评估了所提出遗忘反演攻击的有效性。实验结果表明,所提出的攻击能够揭示被遗忘数据的敏感信息。因此,我们识别出三种可能的防御措施,它们有助于缓解所提出的攻击,但代价是降低遗忘后模型的效用。本文研究揭示了机器遗忘与被遗忘数据隐私之间一个尚未得到充分探索的缺口,强调需要谨慎设计相关机制,以在实现遗忘的同时不泄露被遗忘数据的信息。

英文摘要:

Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning mainly focus on the efficacy and efficiency of unlearning methods, while neglecting the investigation of the privacy vulnerability during the unlearning process. With two versions of a model available to an adversary, that is, the original model and the unlearned model, machine unlearning opens up a new attack surface. In this paper, we conduct the first investigation to understand the extent to which machine unlearning can leak the confidential content of the unlearned data. Specifically, under the Machine Learning as a Service setting, we propose unlearning inversion attacks that can reveal the feature and label information of an unlearned sample by only accessing the original and unlearned model. The effectiveness of the proposed unlearning inversion attacks is evaluated through extensive experiments on benchmark datasets across various model architectures and on both exact and approximate representative unlearning approaches. The experimental results indicate that the proposed attack can reveal the sensitive information of the unlearned data. As such, we identify three possible defenses that help to mitigate the proposed attacks, while at the cost of reducing the utility of the unlearned model. The study in this paper uncovers an underexplored gap between machine unlearning and the privacy of unlearned data, highlighting the need for the careful design of mechanisms for implementing unlearning without leaking the information of the unlearned data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑