AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
This addresses the vulnerability of deep learning classifiers to adversarial attacks, potentially aiding in developing more robust models, though it appears incremental as it builds on existing attack methods.
The paper tackles the problem of generating inconspicuous adversarial attacks on image classifiers by introducing AdvFlow, a black-box method that uses normalizing flows to model adversarial example density, resulting in competitive performance on defended classifiers.
Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these classifiers, hopefully leading to more robust ones. In this paper, we introduce AdvFlow: a novel black-box adversarial attack method on image classifiers that exploits the power of normalizing flows to model the density of adversarial examples around a given target image. We see that the proposed method generates adversaries that closely follow the clean data distribution, a property which makes their detection less likely. Also, our experimental results show competitive performance of the proposed approach with some of the existing attack methods on defended classifiers. The code is available at https://github.com/hmdolatabadi/AdvFlow.