Shaopeng Fu

~Shaopeng_Fu1

3

论文总数

1.5

年均投稿

5.9

平均评分

接收情况2/3

会议分布

ICLR

2

NeurIPS

1

发表论文 (3 篇)

20252 篇

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence

NeurIPS 2025Poster

Representation Confusion: Towards Representation Backdoor on CLIP via Concept Activation

ICLR 2025Rejected

20241 篇

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach

ICLR 2024Poster

合作者 (9)

Jingfeng Zhang1 篇

Liang Ding1 篇

Junchi Liao1 篇

Tianhao Huang1 篇