2021-10-28 | 读Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
动机Sparse adversarial attacks can fool deep neuralnetworks (DNNs) by only perturbing a few pixels(regularized by‘0norm). Recent efforts combineit with another‘∞imperceptible on the pertur-bation magnitudes. The resultant sparse and im-perceptible at
原创
2021-10-29 19:59:16 ·
448 阅读 ·
0 评论