Sparsity in neural networks can improve their privacy
arXiv:2304.10553v22 citationsh-index: 4
Originality Synthesis-oriented
AI Analysis
This work addresses privacy concerns in machine learning for users of neural networks, but it is incremental as it extends existing literature.
The paper investigates how sparsity in neural networks enhances robustness against membership inference attacks, finding that it improves privacy while maintaining similar task performance.
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.