Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning
Stochastic Activation Pruning (SAP) (Dhillon et al., 2018) is a defense to adversarial examples that was attacked and found to be broken by the "Obfuscated Gradients" paper (Athalye et al., 2018). We discover a flaw in the re-implementation that artificially weakens SAP. When SAP is applied properly, the proposed attack is not effective. However, we show that a new use of the BPDA attack technique can still reduce the accuracy of SAP to 0.1%.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to def…
Adversarial AttackAdversarial DefenseBarrage of Random Transforms for Adversarially Robust Defense
Defenses against adversarial examples, when using the ImageNet dataset, are historically easy to defeat. The common understanding is that a combination of simple image transformations and other various defenses are insuf…
Gradient Obfuscation Checklist Test Gives a False Sense of Security
One popular group of defense techniques against adversarial attacks is based on injecting stochastic noise into the network. The main source of robustness of such stochastic defenses however is often due to the obfuscati…
Encryption Inspired Adversarial Defense for Visual Classification
Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this…
Adversarial DefenseClassificationGeneral ClassificationImbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
Evaluating the robustness of a defense model is a challenging task in adversarial robustness research. Obfuscated gradients have previously been found to exist in many defense methods and cause a false signal of robustne…
Adversarial Robustness