1 code implementation • 26 Oct 2022 • Jiebao Zhang, Wenhua Qian, Rencan Nie, Jinde Cao, Dan Xu
We study the attack performance and computation cost of the attack method based on the Hessian with a limited number of perturbation pixels.
1 code implementation • 12 Jul 2022 • Jiebao Zhang, Wenhua Qian, Rencan Nie, Jinde Cao, Dan Xu
Adversarial training is a simple and effective defense method to improve the robustness of CNNs to adversarial examples.