Revisiting Activation Function Design for Improving Adversarial Robustness at Scale

Cihang Xie, Mingxing Tan, Boqing Gong, Alan Yuille, Quoc V Le

Keywords: adversarial training, activation function, neural network architecture

Abstract:

Modern ConvNets typically use ReLU activation function. Recently smooth activation functions have been used to improve their accuracy. Here we study the role of smooth activation function from the perspective of adversarial robustness. We find that ReLU activation function significantly weakens adversarial training due to its non-smooth nature. Replacing ReLU with its smooth alternatives allows adversarial training to find harder adversarial training examples and to compute better gradient updates for network optimization.

We focus our study on the large-scale ImageNet dataset. On ResNet-50, switching from ReLU to the smooth activation function SILU improves adversarial robustness from 33.0% to 42.3%, while also improving accuracy by 0.9% on ImageNet. Smooth activation functions also scale well with larger networks: it helps EfficientNet-L1 to achieve 82.2% accuracy and 58.6% robustness, largely outperforming the previous state-of-the-art defense by 9.5% for accuracy and 11.6% for robustness. Models are available at https://rb.gy/qt8jya.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

TL;DR: ReLU significantly weakens adversarial training, but its smooth approximations can fix this issue