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 2501.16663cs.CRcs.AI
收藏

数据复制:机器遗忘中的一种新型多用途攻击范式

Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning

University of Technology Sydney(新南威尔士大学);City University of Macau(澳门城市大学);Griffith University(格里菲斯大学);CISPA Helmholtz Center for Information Security(信息安全霍普夫研究中心)

Dayong Ye, Tianqing Zhu, Jiayang Li, Kun Gao, Bo Liu, Leo Yu Zhang, Wanlei Zhou, Yang Zhang

AI总结:

本文首次全面研究了数据复制在标准、联邦和强化机器遗忘中的安全威胁,提出三种规避检测的近似复制攻击方法,发现该攻击可导致从头训练等遗忘方法失效、引发模型退化并成功逃避去重检测。

摘要:

数据复制是数据集中普遍存在的问题。现有研究表明,训练数据集中存在的复制数据会显著影响模型性能和数据隐私。然而,数据复制对遗忘过程的影响在很大程度上仍未被探索。本文填补了这一空白,率先对数据复制的角色进行了全面调查,不仅涵盖标准机器遗忘,还包括联邦遗忘和强化遗忘范式。具体而言,我们提出一种对手,该对手复制目标模型训练集的一个子集并将其纳入训练集。训练完成后,对手请求模型所有者遗忘此复制子集,并分析其对遗忘后模型的影响。例如,对手可以通过揭示以下情况来挑战模型所有者:尽管努力进行遗忘,复制子集的影响仍残留在模型中。此外,为规避去重技术的检测,我们为对手提出了三种新颖的近似复制方法,每种方法均针对特定的遗忘范式量身定制。随后,我们考察了在应用去重技术时它们对遗忘过程的影响。我们的发现揭示了几个关键洞察:1)黄金标准遗忘方法,即从头开始重新训练,在某些条件下无法有效执行遗忘;2)遗忘复制数据可能在特定场景下导致显著的模型退化;以及3)精心制作的复制数据可以逃避去重方法的检测。

英文摘要:

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data duplication on the unlearning process remains largely unexplored. This paper addresses this gap by pioneering a comprehensive investigation into the role of data duplication, not only in standard machine unlearning but also in federated and reinforcement unlearning paradigms. Specifically, we propose an adversary who duplicates a subset of the target model's training set and incorporates it into the training set. After training, the adversary requests the model owner to unlearn this duplicated subset, and analyzes the impact on the unlearned model. For example, the adversary can challenge the model owner by revealing that, despite efforts to unlearn it, the influence of the duplicated subset remains in the model. Moreover, to circumvent detection by de-duplication techniques, we propose three novel near-duplication methods for the adversary, each tailored to a specific unlearning paradigm. We then examine their impacts on the unlearning process when de-duplication techniques are applied. Our findings reveal several crucial insights: 1) the gold standard unlearning method, retraining from scratch, fails to effectively conduct unlearning under certain conditions; 2) unlearning duplicated data can lead to significant model degradation in specific scenarios; and 3) meticulously crafted duplicates can evade detection by de-duplication methods.

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。

↑