Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing

24 Mar 2023  ·  Lin Li, Michael Spratling ·

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense against such adversarial attacks. This work focuses on improving adversarial training to boost adversarial robustness. We first analyze, from an instance-wise perspective, how adversarial vulnerability evolves during adversarial training. We find that during training an overall reduction of adversarial loss is achieved by sacrificing a considerable proportion of training samples to be more vulnerable to adversarial attack, which results in an uneven distribution of adversarial vulnerability among data. Such "uneven vulnerability", is prevalent across several popular robust training methods and, more importantly, relates to overfitting in adversarial training. Motivated by this observation, we propose a new adversarial training method: Instance-adaptive Smoothness Enhanced Adversarial Training (ISEAT). It jointly smooths both input and weight loss landscapes in an adaptive, instance-specific, way to enhance robustness more for those samples with higher adversarial vulnerability. Extensive experiments demonstrate the superiority of our method over existing defense methods. Noticeably, our method, when combined with the latest data augmentation and semi-supervised learning techniques, achieves state-of-the-art robustness against $\ell_{\infty}$-norm constrained attacks on CIFAR10 of 59.32% for Wide ResNet34-10 without extra data, and 61.55% for Wide ResNet28-10 with extra data. Code is available at https://github.com/TreeLLi/Instance-adaptive-Smoothness-Enhanced-AT.

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here