Google Research

Improving Adversarial Robustness via Guided Complement Entropy

International Conference on Computer Vision (ICCV) (2019)

Abstract

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by utilizing adversarial training or model distillation, which adds additional procedures to model training. In this paper, we propose a new training paradigm called Guided Complement Entropy (GCE) that is capable of achieving “adversarial defense for free,” which involves no additional procedures in the process of improving adversarial robustness. In addition to maximizing model probabilities on the ground-truth class like cross entropy, we neutralize its probabilities on the incorrect classes along with a “guided” term to balance between these two terms. We show in the experiments that our method achieves better model robustness with even better performance compared to the commonly used cross entropy training objective. We also show that our method can be used orthogonal to adversarial training across well known methods with noticeable robustness gain. To the best of our knowledge, our approach is the first one that improves model robustness without compromising performance.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work