Código QR (código de barras bidimensional)

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...

ver descrição completa

Na minha lista:
Principais autores: 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
Formato: Artigo
Idioma:Inglês
Publicado em: KeAi Communications Co., Ltd. 2025-01-01
coleção:Journal of Information and Intelligence
Assuntos:
Machine learning
Membership inference defenses
Preemptive exclusion
Knowledge distillation
Acesso em linha:http://www.sciencedirect.com/science/article/pii/S2949715924000556
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

Registros relacionados