关注
Hao Li
Hao Li
在 buaa.edu.cn 的电子邮件经过验证
标题
引用次数
引用次数
年份
MFair: Mitigating Bias in Healthcare Data through Multi-Level and Multi-Sensitive-Attribute Reweighting Method
Y Zhu, J An, E Zhou, L An, J Gao, H Li, H Feng, B Hou, W Tang, C Pan, ...
arXiv preprint arXiv:2306.04118, 2023
42023
ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings
H Wang, H Li, M Huang, L Sha
Proceedings of the 2024 Conference on Empirical Methods in Natural Language …, 2024
3*2024
Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
Q Ren, H Li, D Liu, Z Xie, X Lu, Y Qiao, L Sha, J Yan, L Ma, J Shao
arXiv preprint arXiv:2410.10700, 2024
2024
系统目前无法执行此操作,请稍后再试。
文章 1–3