Optimizing membership inference attacks against low self-influence samples by distilled shadow models and inference models

Machine learning models face increasing threats from membership inference attacks, which aim to infer sample membership. Sample membership represents whether or not a particular data sample is included in the training set of a given model and is considered a fundamental form of privacy leakage. Rece...

Szczegółowa specyfikacja

Opis bibliograficzny

Główni autorzy:	Jiacheng Xu, Chengxiang Tan
Format:	Artigo
Język:	Inglês
Wydane:	PeerJ Inc. 2025-10-01
Seria:	PeerJ Computer Science
Hasła przedmiotowe:	AI security Data privacy Membership inference attack Likelihood ratio attack Privacy protection
Dostęp online:	https://peerj.com/articles/cs-3269.pdf
Etykiety:	Dodaj etykietę Nie ma etykietki, Dołącz pierwszą etykiete!