by Shaopeng Fu Papers
2 papers found
Conference
Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
Shaopeng Fu, Liang Ding, Jingfeng ZHANG et al.
NEURIPS 2025arXiv:2502.04204
6
citations
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
Shaopeng Fu, Di Wang
ICLR 2024arXiv:2310.06112
4
citations