科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ arXiv2026-09-04· cs.CR

Machine Unlearning as Private Retroactive Algorithms

Haim Kaplan, Refael Kohen, Yishay Mansour, Kobbi Nissim, Uri Stemmer

原始摘要(英文原文)· Original abstract
Machine unlearning typically aims to emulate retraining from scratch: upon a deletion request, the unlearning algorithm should produce an outcome that would have been obtained had the deleted point never been included. Recent work has shown that this emulation requirement carries no meaningful privacy semantics against an adversary who observes a sequence of releases. Machine unlearning is thus not a privacy question per se, but rather a data maintenance question, which is precisely the subject of retroactive algorithms. These are algorithms supporting modifications of past operations, guaranteeing that all subsequent answers reflect the revised history as if it had always been in force. We put forward a definition of private retroactive algorithms, combining the retroactivity requirement with differential privacy under continual observation. We present constructions achieving both privacy and retroactivity at no asymptotic cost over privacy alone for linear statistics, clustering, and histograms, alongside impossibility results.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Machine Unlearning as Private Retroactive Algorithms — 科研速览 Science Skim