Abstract
The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs). However, the performance of emerging attacks is negatively impacted when fooling DNNs tailored for high-resolution images. One of the explanations is that these methods usually focus on attacking the entire image, regardless of its spatial semantic information, and thereby encounter the notorious curse of dimensionality. To this end, we propose a pixel correlation-based attentional black-box adversarial attack, termed as PICA. Firstly, we take only one of every two neighboring pixels in the salient region as the target by leveraging the attentional mechanism and pixel correlation of images, such that the dimension of the black-box attack reduces. After that, a general multiobjective evolutionary algorithm is employed to traverse the reduced pixels and generate perturbations that are imperceptible by the human vision. Extensive experimental results have verified the effectiveness of the proposed PICA on the ImageNet dataset. More importantly, PICA is computationally more efficient to generate high-resolution adversarial examples compared with the existing black-box attacks.
Abstract (translated)
URL
https://arxiv.org/abs/2101.07538
