论文标题
advflow：使用标准化流量的不起眼的黑盒对抗攻击
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
论文作者
论文摘要
深度学习分类器容易受到其投入的精心制作，不可察觉的变化，称为对抗性攻击。在这方面，对强大攻击模型的研究阐明了这些分类器中脆弱性的来源，希望会导致更健壮的分类器。在本文中，我们介绍了Advflow：一种新型的黑框对抗攻击方法，对图像分类器进行了利用，该方法利用了标准化流的功能，以建模给定目标图像围绕给定目标图像的对抗性示例的密度。我们看到，所提出的方法生成了遵循清洁数据分布的对手，该属性的可能性降低了。同样，我们的实验结果表明，对辩护分类器的一些现有攻击方法，提出的方法的竞争性能。该代码可在https://github.com/hmdolatabadi/advflow上找到。
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.
