Transfer adversarial attacks raise critical security concerns in real-world, black-box scenarios. However, the actual progress of this field is difficult to assess due to two common limitations in existing evaluations. First, different methods are often not systematically and fairly evaluated in a one-to-one comparison. Second, only transferability is evaluated but another key attack property, stealthiness, is largely overlooked. In this work, we design good practices to address these limitations, and we present the first comprehensive evaluation of transfer attacks, covering 23 representative attacks against 9 defenses on ImageNet. In particular, we propose to categorize existing attacks into five categories, which enables our systematic category-wise analyses. These analyses lead to new findings that even challenge existing knowledge and also help determine the optimal attack hyperparameters for our attack-wise comprehensive evaluation. We also pay particular attention to stealthiness, by adopting diverse imperceptibility metrics and looking into new, finer-grained characteristics. Overall, our new insights into transferability and stealthiness lead to actionable good practices for future evaluations.
翻译:对抗性转移攻击在现实世界、黑盒情景中提出了重要的安全关切,然而,由于现有评价中存在两个共同的局限性,这一领域的实际进展难以评估。首先,不同方法往往没有在一对一的比较中进行系统和公正的评价。第二,仅评估可转移性,但又基本上忽视了另一个关键攻击财产,即隐形财产。在这项工作中,我们设计了解决这些限制的良好做法,我们提出了对转移攻击的第一次全面评估,包括23次针对图像网9项防御的具有代表性的攻击。特别是,我们提议将现有攻击分为五类,以便能够进行系统的分类分析。这些分析导致新的发现,甚至挑战了现有知识,并有助于确定我们攻击性综合评价的最佳超参数。我们还特别注意隐形性,采用不同的不易感度指标,并研究新的细微的特征。总体而言,我们对可转移性和隐性的新认识导致未来评价的可操作的良好做法。</s>