Protecting the Undeleted in Machine Unlearning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cohen, Aloni, Kohen, Refael, Nissim, Kobbi, Stemmer, Uri
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912912074866688
author Cohen, Aloni
Kohen, Refael
Nissim, Kobbi
Stemmer, Uri
author_facet Cohen, Aloni
Kohen, Refael
Nissim, Kobbi
Stemmer, Uri
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_16697
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Protecting the Undeleted in Machine Unlearning
Cohen, Aloni
Kohen, Refael
Nissim, Kobbi
Stemmer, Uri
Machine Learning
Data Structures and Algorithms
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.
title Protecting the Undeleted in Machine Unlearning
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2602.16697