Crowd counting, which is significantly important for estimating the number of people in safety-critical scenes, has been shown to be vulnerable to adversarial examples in the physical world (e.g., adversarial patches). Though harmful, adversarial examples are also valuable for assessing and better understanding model robustness. However, existing adversarial example generation methods in crowd counting scenarios lack strong transferability among different black-box models. Motivated by the fact that transferability is positively correlated to the model-invariant characteristics, this paper proposes the Perceptual Adversarial Patch (PAP) generation framework to learn the shared perceptual features between models by exploiting both the model scale perception and position perception. Specifically, PAP exploits differentiable interpolation and density attention to help learn the invariance between models during training, leading to better transferability. In addition, we surprisingly found that our adversarial patches could also be utilized to benefit the performance of vanilla models for alleviating several challenges including cross datasets and complex backgrounds. Extensive experiments under both digital and physical world scenarios demonstrate the effectiveness of our PAP.
翻译:人群计数对于估计在安全临界场景中的人数非常重要,但事实证明,这种计数在物理界(例如对立阵形)中很容易受到对抗性实例的影响。虽然有害的敌对性实例对评估和更好地理解模型稳健性也十分宝贵,但现有的人群计数假设中的对抗性实例生成方法在不同黑箱模型之间缺乏很强的可转移性。由于可转移性与模式和差异性特征有着积极的联系,本文件提议了概念性对立调(PAP)生成框架,以通过利用模型规模感知和位置感知来了解各种模型之间的共同概念特征。具体地说,PAP利用不同的内推法和密度关注来帮助了解各种模型之间的差异,从而导致更好的可转移性。此外,我们惊讶地发现,我们的对抗性补丁也可用于利用香草模型的绩效来缓解包括交叉数据集和复杂背景在内的若干挑战。在数字和物理世界情景下进行的广泛实验显示了我们的PAP的有效性。