Sparsity in neural networks can improve their privacy

Add code
Apr 20, 2023
Antoine Gonon, Léon Zheng, Clément Lalanne, Quoc-Tung Le, Guillaume Lauga, Can Pouliquen
Figure 1 for Sparsity in neural networks can improve their privacy
Figure 2 for Sparsity in neural networks can improve their privacy
Figure 3 for Sparsity in neural networks can improve their privacy
Figure 4 for Sparsity in neural networks can improve their privacy

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of the network, while preserving comparable performances on the task at hand. This empirical study completes and extends existing literature.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon