Robustness May Be at Odds with Accuracy

TLDR

The authors prove that a trade‑off between standard accuracy and adversarial robustness exists in a simple, natural setting. The study reveals that pursuing adversarial robustness can reduce standard accuracy, increase resource demands, and that robust models learn distinct, more perceptually aligned representations, a pattern also seen in complex settings.

Abstract

We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of standard accuracy. We demonstrate that this trade-off between the standard accuracy of a model and its robustness to adversarial perturbations provably exists in a fairly simple and natural setting. These findings also corroborate a similar phenomenon observed empirically in more complex settings. Further, we argue that this phenomenon is a consequence of robust classifiers learning fundamentally different feature representations than standard classifiers. These differences, in particular, seem to result in unexpected benefits: the representations learned by robust models tend to align better with salient data characteristics and human perception.