Survey: Leakage and Privacy at Inference Time

Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance since commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data. We provide a comprehensive survey of co...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2023-07, Vol.45 (7), p.9090-9108
Hauptverfasser:	Jegorova, Marija, Kaul, Chaitanya, Mayor, Charlie, O'Neil, Alison Q., Weir, Alexander, Murray-Smith, Roderick, Tsaftaris, Sotirios A.
Format:	Artikel
Sprache:	eng
Schlagworte:	adversarial defences Computational modeling data anonymization Data leakage Data models Data privacy feature leakage Glass box Inference inference-time attacks Leakage Machine learning machine unlearning membership inference Privacy privacy attacks and defences property inference Task analysis Taxonomy Training Training data verifying forgetting
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!