Skip to yearly menu bar Skip to main content

Workshop: A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

Jie Wang · Zhaoxia Yin · Jing Jiang · Yang Du


Recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, We propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA. By considering the spatial semantic information of images, we firstly take advantage of the attention map to determine the perturbed pixels. Then, a large-scale multiobjective evolutionary algorithm is employed to traverse the reduced pixels in the salient region. Extensive experimental results have verified the effectiveness of the proposed LMOA on the ImageNet dataset.

Chat is not available.