← Search

Xuelong Dai

2 accepted papers

2025

Improving Transferable Targeted Attacks with Feature Tuning Mixup

CVPR 2025poster

Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferable targeted attacks that can mislead DNN models into predicting specific target classes. While various methods have been…

2023

Physical-World Optical Adversarial Attacks on 3D Face Recognition

CVPR 2023poster

The success rate of current adversarial attacks remains low on real-world 3D face recognition tasks because the 3D-printing attacks need to meet the requirement that the generated points should be adjacent to the surface, which limits the adversarial example' searching space. Additionally, they have…