Showing 2024Show all
2 papers · 1 filter
cs.CV2024
Improving Transferable Targeted Attacks with Feature Tuning Mixup
Kaisheng Liang, Xuelong Dai, Yanjie Li +2
Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferab…
cs.CV2024
Transferable 3D Adversarial Shape Completion using Diffusion Models
Xuelong Dai, Bin Xiao
Recent studies that incorporate geometric features and transformers into 3D point cloud feature learning have significantly improved the performance of 3D deep-learning models. How…