Minghui Li

4

Papers

5

Total Citations

Papers (4)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization

Test-Time Backdoor Detection for Object Detection Models

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

Detecting and Corrupting Convolution-based Unlearnable Examples