A Perturbation Analysis of Input Transformations for Adversarial Attacks

The existence of adversarial examples, or intentional mis-predictions constructed from small changes to correctly predicted examples, is one of the most significant challenges in neural network research today. Ironically, many new defenses are based on a simple observation - the adversarial inputs themselves are not robust and small perturbations to the attacking input often recover the desired prediction. While the intuition is somewhat clear, a detailed understanding of this phenomenon is missing from the research literature. This paper presents a comprehensive experimental analysis of when and why perturbation defenses work and potential mechanisms that could explain their effectiveness (or ineffectiveness) in different settings.