Imperceptible Adversarial Attack via Invertible Neural Networks

1 code implementation • 28 Nov 2022 • Zihan Chen, Ziyue Wang, JunJie Huang, Wentao Zhao, Xiao Liu, Dejian Guan

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples.

Adversarial Attack