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 2610.21799cs.CL
收藏

行为遗忘并非机器删除中的隐私

Behavioral Forgetting Is Not Privacy in Machine Unlearning

Georgia Institute of Technology(佐治亚理工学院)

Tyler Lizzo, Larry Heck

AI总结:

该研究指出机器删除的现有评估标准不足,通过跨语言查询案例发现多语言模型在不同语言查询下遗忘效果差异大,推动需评估访问路径泛化性与对抗性可恢复性。

摘要:

机器删除旨在从大语言模型中移除目标信息,但现有评估通常仅在指定的基准分布上衡量遗忘效果。本文认为,这种行为遗忘不足以作为面向隐私的机器删除的标准,评估应转而测试遗忘是否在可恢复相同信息的访问路径中持续存在。我们通过跨语言查询的受控案例研究证明了这一点:在多个多语言模型家族中,当用不同语言和脚本查询语义等效信息时,遗忘效果存在显著差异。因此,单条访问路径足以暴露行为遗忘与信息不可访问之间的实际差距,这推动了除分布内遗忘之外,对访问路径泛化性和对抗性可恢复性的更广泛评估。

英文摘要:

Machine unlearning aims to remove targeted information from large language models, but existing evaluations often measure forgetting only on a designated benchmark distribution. We argue that such behavioral forgetting is an insufficient standard for privacy-oriented unlearning, and that evaluation should instead test whether forgetting persists across the access paths through which the same information may be recovered. We demonstrate this with a controlled case study of cross-lingual querying: across multiple multilingual model families, forgetting varies substantially when semantically equivalent information is queried in different languages and scripts. A single access path is therefore enough to expose a real gap between behavioral forgetting and information inaccessibility, motivating broader evaluation of access-path generalization and adversarial recoverability alongside in-distribution forgetting.

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。

↑