Dual defense: Combining preemptive exclusion of members and knowledge distillation to mitigate membership inference attacks

Membership inference (MI) attacks threaten user privacy through determining if a given data example has been used to train a target model. Existing MI defenses protect the membership privacy through preemptive exclusion of members techniques and knowledge distillation. Unfortunately, using either of...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Jun Niu, Peng Liu, Chunhui Huang, Yangming Zhang, Moxuan Zeng, Kuo Shen, Yangzhong Wang, Suyu An, Yulong Shen, Xiaohong Jiang, Jianfeng Ma, He Wang, Gaofei Wu, Anmin Fu, Chunjie Cao, Xiaoyan Zhu, Yuqing Zhang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	KeAi Communications Co., Ltd. 2025-01-01
Schriftenreihe:	Journal of Information and Intelligence
Schlagworte:	Machine learning Membership inference defenses Preemptive exclusion Knowledge distillation
Online-Zugang:	http://www.sciencedirect.com/science/article/pii/S2949715924000556
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!