Decoupling Generalizability and Membership Privacy Risks in Neural Networks

TMLR Paper5258 Authors

Abstract:

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense approaches implies the potential to decouple generalizability and privacy risks to maximize privacy gain. In this paper, we identify that the model’s generalization and privacy risks exist in different regions in deep neural network architectures. Based on the observations that we investigate, we propose Privacy-Preserving
Training Principle (PPTP) to protect model components from privacy risks while minimizing the loss in generalizability. Through extensive evaluations, our approach shows significantly better maintenance in model generalizability while enhancing privacy preservation.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Arno_Solin1

Submission Number: 5258