#artificial intelligence
May 2026
Batch Normalization Amplifies Memorization and Privacy Risks
This work investigates the effect of BN layers on the memorization of atypical or outlier samples and its implications for privacy leakage, and provides both practical and theoretical insights into how normalization layers can amplify the influence of rare or sensitive training examples.
Ngoc Phu Doan, Chongyan Gu, Ihsen Alouani
· arXiv.org · 1 citation