Matryoshka : Exploiting the Over-Parametrization of Deep Learning Models for Covert Data Transmission

High-quality private machine learning (ML) data stored in local data centers becomes a key competitive factor for AI corporations. In this paper, we present a novel insider attack called Matryoshka to reveal the possibility of breaking the privacy of ML data even with no exposed interface. Our attac...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 26. Juli
1. Verfasser:	Pan, Xudong (VerfasserIn)
Weitere Verfasser:	Zhang, Mi, Yan, Yifan, Zhang, Shengyao, Yang, Min
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2024
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article