This paper proposes Evolutionary Multi-objective Optimization (EMO)-based Adversarial Example (AE) design method that performs under black-box setting. Previous gradient-based methods produce AEs by changing all pixels of a target image, while previous EC-based method changes small number of pixels to produce AEs. Thanks to EMO's property of population based-search, the proposed method produces various types of AEs involving ones locating between AEs generated by the previous two approaches, which helps to know the characteristics of a target model or to know unknown attack patterns. Experimental results showed the potential of the proposed method, e.g., it can generate robust AEs and, with the aid of DCT-based perturbation pattern generation, AEs for high resolution images.

中文翻译：

---

使用进化多目标优化的对抗性示例生成

本文提出了基于进化多目标优化 (EMO) 的对抗性示例 (AE) 设计方法，该方法在黑盒设置下执行。以前的基于梯度的方法通过改变目标图像的所有像素来产生 AE，而以前的基于 EC 的方法改变少量像素来产生 AE。由于 EMO 的基于群体搜索的特性，所提出的方法产生了各种类型的 AE，包括定位在前两种方法生成的 AE 之间的 AE，这有助于了解目标模型的特征或了解未知的攻击模式。实验结果表明了所提出方法的潜力，例如，它可以生成鲁棒的 AE，并且在基于 DCT 的扰动模式生成的帮助下，可以生成高分辨率图像的 AE。