← Search

Xuelong Dai*

2 accepted papers

2024

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

ECCV 2024poster

"Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms. However, previous attack methods often directly inject Proj…