Beware the black-box: On the robustness of recent defenses to adversarial examples
Entropy , Volume 23 - Issue 10 p. 1359
Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analyses of these defenses to include adaptive black-box adversaries. Our evaluation is done on nine defenses including Barrage of Random Transforms, ComDefend, Ensemble Diversity, Feature Distillation, The Odds are Odd, Error Correcting Codes, Distribution Classifier Defense, K-Winner Take All and Buffer Zones. Our investigation is done using two black-box adversarial models and six widely studied adversarial attacks for CIFAR-10 and Fashion-MNIST datasets. Our analyses show most recent defenses (7 out of 9) provide only marginal improvements in security (<25%), as compared to undefended networks. For every defense, we also show the relationship between the amount of data the adversary has at their disposal, and the effectiveness of adaptive black-box attacks. Overall, our results paint a clear picture: defenses need both thorough white-box and black-box analyses to be considered secure. We provide this large scale study and analyses to motivate the field to move towards the development of more robust black-box defenses.
|eBay Inc., San Jose, CA, USA|
|Organisation||Centrum Wiskunde & Informatica, Amsterdam (CWI), The Netherlands|
Mahmood, K, Gurevin, D, van Dijk, M.E, & Nguyen, P.H. (2021). Beware the black-box: On the robustness of recent defenses to adversarial examples. Entropy, 23(10). doi:10.3390/e23101359