Active Membership Inference Attack under Local Differential Privacy in Federated Learning
Document Type
Conference Proceeding
Publication Date
1-1-2023
Abstract
Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection through a coordinating server. In this paper, we propose a new active membership inference (AMI) attack carried out by a dishonest server in FL. In AMI attacks, the server crafts and embeds malicious parameters into global models to effectively infer whether a target data sample is included in a client's private training data or not. By exploiting the correlation among data features through a non-linear decision boundary, AMI attacks with a certified guarantee of success can achieve severely high success rates under rigorous local differential privacy (LDP) protection; thereby exposing clients' training data to significant privacy risk. Theoretical and experimental results on several benchmark datasets show that adding sufficient privacy-preserving noise to prevent our attack would significantly damage FL's model utility.
Identifier
85165171361 (Scopus)
Publication Title
Proceedings of Machine Learning Research
e-ISSN
26403498
First Page
5714
Last Page
5730
Volume
206
Grant
CNS-1935923
Fund Ref
National Science Foundation
Recommended Citation
Nguyen, Truc; Lai, Phung; Tran, Khang; Phan, Nhat Hai; and Thai, My T., "Active Membership Inference Attack under Local Differential Privacy in Federated Learning" (2023). Faculty Publications. 2094.
https://digitalcommons.njit.edu/fac_pubs/2094
