Xiao-Shan Gao

8

Papers

10

Total Citations

Papers (8)

PowerMLP: An Efficient Version of KAN

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Detection and Defense of Unlearnable Examples

Generalization Bound and New Algorithm for Clean-Label Backdoor Attack

Toward Availability Attacks in 3D Point Clouds

Analyzing the Power of Chain of Thought through Memorization Capabilities

NeurIPS 2025arXiv

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization