Picture for Mingkun Zhang

Mingkun Zhang

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

Add code
Oct 30, 2024
Viaarxiv icon

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

Add code
Aug 12, 2024
Viaarxiv icon

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

Add code
Dec 16, 2023
Viaarxiv icon