arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16697cs.LGcs.DS
收藏

保护未删除的数据在机器遗忘中

Protecting the Undeleted in Machine Unlearning

University of Chicago(芝加哥大学);Tel Aviv University(特拉维夫大学);Georgetown University(乔治城大学)

Aloni Cohen, Refael Kohen, Kobbi Nissim, Uri Stemmer

AI总结:

本文提出了一种新的安全定义,旨在保护未删除数据免受删除操作带来的隐私泄露,并支持基本功能如求和和统计学习。

摘要:

机器遗忘旨在从训练好的模型中移除特定数据点,通常力求模拟“完美重训练”,即产生从未包含删除数据的模型。我们证明这种做法以及支持它的安全定义对剩余(未删除)数据点存在显著的隐私风险。我们提出了一种重构攻击,表明对于某些任务,可以安全地在不删除的情况下计算,一个机制遵循完美重训练允许对手仅控制ω(1)的数据点通过发出删除请求来重构几乎整个数据集。我们调查了现有的机器遗忘定义,显示它们要么容易受到此类攻击,要么过于严格,无法支持基本功能如精确求和。为了解决这个问题,我们提出了一种新的安全定义,专门保护未删除数据免受其他点删除引起的泄漏。我们显示我们的定义允许几种基本功能,如公告板、求和和统计学习。

英文摘要:

Machine unlearning aims to remove specific data points from a trained model, often striving to emulate "perfect retraining", i.e., producing the model that would have been obtained had the deleted data never been included. We demonstrate that this approach, and security definitions that enable it, carry significant privacy risks for the remaining (undeleted) data points. We present a reconstruction attack showing that for certain tasks, which can be computed securely without deletions, a mechanism adhering to perfect retraining allows an adversary controlling merely $ω(1)$ data points to reconstruct almost the entire dataset merely by issuing deletion requests. We survey existing definitions for machine unlearning, showing they are either susceptible to such attacks or too restrictive to support basic functionalities like exact summation. To address this problem, we propose a new security definition that specifically safeguards undeleted data against leakage caused by the deletion of other points. We show that our definition permits several essential functionalities, such as bulletin boards, summations, and statistical learning.

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。

↑