F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns

no code implementations • 23 Oct 2023 • Yaguan Qian, Chenyu Zhao, Zhaoquan Gu, Bin Wang, Shouling Ji, Wei Wang, Boyang Zhou, Pan Zhou

We propose a Feature-Focusing Adversarial Training (F$^2$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns.

Adversarial Robustness Disentanglement +2