AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

1 code implementation • 24 Jul 2023 • Xuelong Dai, Kaisheng Liang, Bin Xiao

Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques.

Adversarial Defense

StyLess: Boosting the Transferability of Adversarial Examples

1 code implementation • CVPR 2023 • Kaisheng Liang, Bin Xiao

Our method can prevent adversarial examples from using non-robust style features and help generate transferable perturbations.