Metraipolis › archive › dc_4e1c4bdaa60f

Machine Unlearning as Private Retroactive Algorithms — arXiv:2609.05329

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05329
License (as archived)
CC0-1.0
Archived
2026-10-16T22:51:22.128Z
SHA-256 of the archived text
a5c75737971a37ada90167b5a43379f7c0fa7de89e21a68231e558a80d70f3e4
Stable URL of this page
https://metraipolis.com/documento/dc_4e1c4bdaa60f

How to cite

Machine Unlearning as Private Retroactive Algorithms — arXiv:2609.05329 — arXiv (en), https://arxiv.org/abs/2609.05329 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e1c4bdaa60f (Metraipolis archive dc_4e1c4bdaa60f, sha256 a5c75737971a37ada90167b5a43379f7c0fa7de89e21a68231e558a80d70f3e4)
BibTeX
@misc{dc4e1c4bdaa60f,
  title = {Machine Unlearning as Private Retroactive Algorithms — arXiv:2609.05329},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05329},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e1c4bdaa60f; sha256 a5c75737971a37ada90167b5a43379f7c0fa7de89e21a68231e558a80d70f3e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05329. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Data Structures and Algorithms (cs.DS).
Pagina del lavoro: https://arxiv.org/abs/2609.05329 — 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 2026-10-16T22:30:54.322Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).