2 papers
cs.CR2025
Generating Adversarial Point Clouds Using Diffusion Model
Ruiyang Zhao, Bingbing Zhu, Chuxuan Tong +2
Adversarial attack methods for 3D point cloud classification reveal the vulnerabilities of point cloud recognition models. This vulnerability could lead to safety risks in critical…
cs.CR2023
RAEDiff: Denoising Diffusion Probabilistic Models Based Reversible Adversarial Examples Self-Generation and Self-Recovery
Fan Xing, Xiaoyi Zhou, Xuefeng Fan +2
Collected and annotated datasets, which are obtained through extensive efforts, are effective for training Deep Neural Network (DNN) models. However, these datasets are susceptible…