Case-Aware Adversarial Training

TL;DR

This paper introduces case-aware adversarial training (CAT), a novel method that efficiently improves neural network robustness against adversarial examples by selectively using the most informative AEs, reducing computation while maintaining effectiveness.

Contribution

The paper proposes a generic, efficient adversarial training scheme that estimates AE informativeness and employs class-level sampling to enhance defense with lower computational cost.

Findings

CAT is up to 3x faster than vanilla adversarial training.

CAT maintains competitive defense effectiveness against adversarial attacks.

The method effectively filters and diversifies AEs to improve training efficiency.

Abstract

The neural network (NN) becomes one of the most heated type of models in various signal processing applications. However, NNs are extremely vulnerable to adversarial examples (AEs). To defend AEs, adversarial training (AT) is believed to be the most effective method while due to the intensive computation, AT is limited to be applied in most applications. In this paper, to resolve the problem, we design a generic and efficient AT improvement scheme, namely case-aware adversarial training (CAT). Specifically, the intuition stems from the fact that a very limited part of informative samples can contribute to most of model performance. Alternatively, if only the most informative AEs are used in AT, we can lower the computation complexity of AT significantly as maintaining the defense effect. To achieve this, CAT achieves two breakthroughs. First, a method to estimate the information degree of adversarial examples is proposed for AE filtering. Second, to further enrich the information that the NN can obtain from AEs, CAT involves a weight estimation and class-level balancing based sampling strategy to increase the diversity of AT at each iteration. Extensive experiments show that CAT is faster than vanilla AT by up to 3x while achieving competitive defense effect.