The success of image perturbations that are designed to fool image classifier
is assessed in terms of both adversarial effect and visual imperceptibility.
The conventional assumption on imperceptibility is that perturbations should
strive for tight $L_p$-norm bounds in RGB space. In this work, we drop this
assumption by pursuing an approach that exploits human color perception, and
more specifically, minimizing perturbation size with respect to perceptual
color distance. Our first approach, Perceptual Color distance C&W (PerC-C&W),
extends the widely-used C&W approach and produces larger RGB perturbations.
PerC-C&W is able to maintain adversarial strength, while contributing to
imperceptibility. Our second approach, Perceptual Color distance Alternating
Loss (PerC-AL), achieves the same outcome, but does so more efficiently by
alternating between the classification loss and perceptual color difference
when updating perturbations. Experimental evaluation shows PerC approaches
outperform conventional $L_p$ approaches in terms of robustness and
transferability, and also demonstrates that the PerC distance can provide added
value on top of existing structure-based methods to creating image
perturbations.

通过以人类色彩知觉为基础的感知色距离来减小图像干扰，以提高对抗性和视觉不可察觉性，在对比 $L_p$ 距离的基础上，创造出两种以感知色距离为基础（PerC-C&W 和 PerC-AL）的图像干扰方式，并证明这种方法在稳健性和可转移性方面优于传统方式。