vix.ing · top · new · best · stats

Evaluating a Simple Retraining Strategy as a Defense Against Adversarial Attacks

2020/07/20 by Nupur Thakur, Thakur, Nupur, Yuzhen Ding +3
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.5.1 #I.5.4 #Integrated Circuits and Semiconductor Failure Analysis #cs.CV

paper · pdf · doi:10.48550/arxiv.2007.09916

16 pages, 11 figures

arxiv created 2020/07/20 · openalex publication_date 2020/07/20 · arxiv updated 2020/07/21 · openalex created_date 2020/07/23 · openalex updated_date 2026/07/28

Abstract

Though deep neural networks (DNNs) have shown superiority over other techniques in major fields like computer vision, natural language processing, robotics, recently, it has been proven that they are vulnerable to adversarial attacks. The addition of a simple, small and almost invisible perturbation to the original input image can be used to fool DNNs into making wrong decisions. With more attack algorithms being designed, a need for defending the neural networks from such attacks arises. Retraining the network with adversarial images is one of the simplest techniques. In this paper, we evaluate the effectiveness of such a retraining strategy in defending against adversarial attacks. We also show how simple algorithms like KNN can be used to determine the labels of the adversarial images needed for retraining. We present the results on two standard datasets namely, CIFAR-10 and TinyImageNet.

Citations

Related