Info
We reveal that the use of Batch Normalization makes the network more vulnerable to adversarial attacks. Work presented at the ICML 2019 workshop Identifying and Understanding Deep Learning Phenomena in Long Beach. Find the paper here and the poster below.
Abstract
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it also reduces robustness to small adversarial input perturbations and noise by double-digit percentages, as we show on five standard datasets. Furthermore, substituting weight decay for batch norm is sufficient to nullify the relationship between adversarial vulnerability and the input dimension. Our work is consistent with a mean-field analysis that found that batch norm causes exploding gradients.
Poster
