Metraipolis › archive › dc_b68c116141df
Modeling Deletion Requests in Machine Unlearning — arXiv:2610.04310
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04310
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:29:21.086Z
- SHA-256 of the archived text
a839511cfed94dbd23d51615efc764ebab29458ef575ae250a25f89478bf117e- Stable URL of this page
https://metraipolis.com/documento/dc_b68c116141df
How to cite
Modeling Deletion Requests in Machine Unlearning — arXiv:2610.04310 — arXiv, https://arxiv.org/abs/2610.04310 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b68c116141df (Metraipolis archive dc_b68c116141df, sha256 a839511cfed94dbd23d51615efc764ebab29458ef575ae250a25f89478bf117e)
BibTeX
@misc{dcb68c116141df,
title = {Modeling Deletion Requests in Machine Unlearning — arXiv:2610.04310},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04310},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b68c116141df; sha256 a839511cfed94dbd23d51615efc764ebab29458ef575ae250a25f89478bf117e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04310. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine unlearning is seen as a promising approach to enable users to exercise the "right to erasure" in the context of AI models. We ask how users might influence the behavior of models when exercising this right. We define two types of behaviors that users might adopt when requesting the deletion of their data: adaptivity and collectivity. Drawing connections between the goals of users in this context and results in stochastic optimization, we demonstrate theoretical gaps between the potential effects of groups of users who do and do not display these behaviors. We then show how techniques from data valuation might be used to design deletion requesters that can significantly alter model behavior in realistic settings. In experiments on computer vision tasks, we demonstrate the differential effects of different models of user behavior and attempt to isolate the impacts of adaptivity and collectivity. Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.CY, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2610.04310 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:25:20.370Z dalla pagina https://arxiv.org/list/cs.CY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).