by Shaopeng Fu Papers
2 papers found
Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
Shaopeng Fu, Liang Ding, Jingfeng ZHANG et al.
NeurIPS 2025posterarXiv:2502.04204
6
citations
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
Shaopeng Fu, Di Wang
ICLR 2024poster