Locally optimal detection of stochastic targeted universal adversarial perturbations

Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test (LO-GLRT) based detector for detecting stochastic targeted universal adversarial perturbations (UAPs) of the classifier inputs. We also describe a supervised training method to learn the detector's parameters, and demonstrate better performance of the detector compared to other detection methods on several popular image classification datasets.

Amish Goel, Pierre Moulin · 2020