arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.07876cs.CRcs.CY
收藏

控制、机密性与被遗忘权

Control, Confidentiality, and the Right to be Forgotten

Aloni Cohen, Adam Smith, Marika Swanberg, Prashant Nalini Vasudevan

AI总结:

本文提出“删除即控制”新形式化框架,允许删除前自由使用数据、删除后施加有效约束,并证明持续发布差分隐私更新模型可满足该框架,且准确度与删除数据点数量无关。

摘要:

近期的数字权利框架赋予用户从存储和处理其个人信息的系统中删除其数据的权利(例如 GDPR 中的“被遗忘权”)。在涉及众多用户交互并存储衍生信息的复杂系统中,删除应如何形式化?我们认为先前的方法存在不足。Cao 和 Yang [2015] 的机器遗忘定义范围过窄,不适用于一般的交互式场景。Garg 等人 [2020] 提出的“删除即机密性”这一自然方法则过于严格:由于要求已删除数据的保密性,它排除了社交功能。我们提出一种新的形式化框架:删除即控制。该框架允许用户的数据在删除前被自由使用,同时在删除后施加一个有意义的约束——从而赋予用户更多控制权。删除即控制为在多样场景中实现删除提供了新途径。我们将其应用于社交功能,并对文献中的多种机器遗忘定义给出了新的统一视角。这一工作通过历史独立性的新型自适应推广来完成。删除即控制还为机器遗忘目标提供了一种新方法,即在尊重用户删除请求的同时维护模型。我们证明,发布一系列在持续发布机制下满足差分隐私的更新模型即可满足删除即控制。与机器遗忘文献中的结果不同,此类算法的准确度不依赖于被删除数据点的数量。

英文摘要:

Recent digital rights frameworks give users the right to delete their data from systems that store and process their personal information (e.g., the "right to be forgotten" in the GDPR). How should deletion be formalized in complex systems that interact with many users and store derivative information? We argue that prior approaches fall short. Definitions of machine unlearning Cao and Yang [2015] are too narrowly scoped and do not apply to general interactive settings. The natural approach of deletion-as-confidentiality Garg et al. [2020] is too restrictive: by requiring secrecy of deleted data, it rules out social functionalities. We propose a new formalism: deletion-as-control. It allows users' data to be freely used before deletion, while also imposing a meaningful requirement after deletion--thereby giving users more control. Deletion-as-control provides new ways of achieving deletion in diverse settings. We apply it to social functionalities, and give a new unified view of various machine unlearning definitions from the literature. This is done by way of a new adaptive generalization of history independence. Deletion-as-control also provides a new approach to the goal of machine unlearning, that is, to maintaining a model while honoring users' deletion requests. We show that publishing a sequence of updated models that are differentially private under continual release satisfies deletion-as-control. The accuracy of such an algorithm does not depend on the number of deleted points, in contrast to the machine unlearning literature.

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。

↑