QR Code

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...

Whakaahuatanga katoa

I tiakina i:
Ngā kaituhi matua: 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
Hōputu: Artigo
Reo:Inglês
I whakaputaina: KeAi Communications Co., Ltd. 2025-01-01
Rangatū:Journal of Information and Intelligence
Ngā marau:
Machine learning
Membership inference defenses
Preemptive exclusion
Knowledge distillation
Urunga tuihono:http://www.sciencedirect.com/science/article/pii/S2949715924000556
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!

Ngā tūemi rite