Defense Against Universal Adversarial Perturbations

Abstract

Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to `any' image can fool a state-of-the-art network classifier to change its prediction about the image label. These `Universal Adversarial Perturbations' pose a serious threat to the success of Deep Learning in practice. We present the first dedicated framework to effectively defend the networks against such perturbations. Our approach learns a Perturbation Rectifying Network (PRN) as `pre-input' layers to a targeted model, such that the targeted model needs no modification. The PRN is learned from real and synthetic image-agnostic perturbations, where an efficient method to compute the latter is also proposed. A perturbation detector is separately trained on the Discrete Cosine Transform of the input-output difference of the PRN. A query image is first passed through the PRN and verified by the detector. If a perturbation is detected, the output of the PRN is used for label prediction instead of the actual image. A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 96.4% success rate. The PRN also generalizes well in the sense that training for one targeted network defends another network with a comparable success rate.