Xiaohu Du - Publications, H-index & Citations

Xiaohu Du

Ant Group

5H指数

17论文数

57被引数

收录论文 3

发表时间

Securing Autonomous Large Language Model Agents: Lessons From OpenClaw 保障自主大型语言模型智能体：来自OpenClaw的经验教训

IEEE SECURITY & PRIVACY

IF3

2026-09-17

PREAI

Xinhao Deng; Yixiang Zhang; Jiaqing Wu; Jiaqi Bai; Sibo Yi; Zhuoheng Zou; Yue Xiao; Rennai Qiu; Jianan Ma; Jialuo Chen; Xiaohu Du; Xiaofang Yang; Shiwen Cui; Changhua Meng; Weiqiang Wang; Jiaxing Song; Ke Xu; Qi Li

TADSOB: Enhancing jailbreaking attacks on LLMs via trajectory-aware dynamic suffix optimization with buffer TADSOB：通过具有缓冲区的轨迹感知动态后缀优化增强大语言模型的越狱攻击

Neurocomputing

IF6.5

2026-09-01

PREAI

Xiaolong Li; Mingrui Lao; Chengsi Du; Yunhao Feng; Xiaohu Du; Liang Bai; Yanming Guo

SEAttack: A self-evolving jailbreak attack to induce toxic responses for non-toxic queries in large language models SEAttack：一种自进化的越狱攻击方法，用于诱导大型语言模型对无害查询产生有害响应

Information Processing & Management

IF6.9

2025-12-12

PREAI

Huijun Liu; Shasha Li; Bin Ji; Xiaohu Du; Xiaopeng Li; Jun null; Jie Yu

研究方向