Early Methods for Detecting Adversarial Images

Dan Hendrycks, Kevin Gimpel

Abstract: Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception. We deploy three methods to detect adversarial images. Adversaries trying to bypass our detectors must make the adversarial image less pathological or they will fail trying. Our best detection method reveals that adversarial images place abnormal emphasis on the lower-ranked principal components from PCA. Other detectors and a colorful saliency map are in an appendix.

Keywords: Computer vision, Deep learning

Conflicts: ttic.edu, uchicago.edu