- Securing Autonomous LLM Agents: Lessons From OpenClaw
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
IEEE Security & Privacy, 2026, SCI - SEAttack: A self-evolving jailbreak attack to induce toxic responses for non-toxic queries in large language models
Huijun Liu, Shasha Li, Bin Ji, Xiaohu Du, Xiaopeng Li, Jun Ma, Jie Yu
Information Processing & Management, 2026, CCF-B - Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations
Yongkang Chen, Xiaohu Du, Xiaotian Zou, Chongyang Zhao, Huan Deng, Hu LI, Xiaohui Kuang
The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), CCF-B
[Paper] - Statement-level Adversarial Attack on Vulnerability Detection Models via Out-Of-Distribution Features
Xiaohu Du, Ming Wen, Haoyu Wang, Zichao Wei, Hai Jin
The 33rd ACM International Conference on the Foundations of Software Engineering (FSE 2025), CCF-A
[Paper] [Code] - Multi-Turn Jailbreaking Large Language Models via Attention Shifting
Xiaohu Du, Fan Mo, Ming Wen, Tu Gu, Huadi Zheng, Hai Jin, Jie Shi
The 39th AAAI Conference on Artificial Intelligence (AAAI 2025), CCF-A
[Paper] - Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning
Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, Hai Jin
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024 Findings)
[Paper] [Code] - An Extensive Study on Adversarial Attack against Pre-trained Models of Code
Xiaohu Du, Ming Wen, Zichao Wei, Shangwen Wang, Hai Jin
The 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE 2023), CCF-A
[Paper] [Code] - Understanding the Bug Characteristics and Fix Strategies of Federated Learning Systems
Xiaohu Du, Xiao Chen, Jialun Cao, Ming Wen, Shing-Chi Cheung, Hai Jin
The 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE 2023). CCF-A
[Paper] [Code] Word-Level Adversarial Text with Robust Adversarial Training
Xiaohu Du, Jie Yu, Shasha Li, Zibo Yi, Hai Liu, Jun Ma
2021 International Joint Conference on Neural Networks (IJCNN 2021), CCF-C
[Paper]- Adversarial Text Attack and Defense: A Review
Xiaohu Du, Hongming Wu, Zibo Yi, Shasha Li, Jun Ma, Jie Yu
Journal of Chinese Information Processing, 2021, CCF-B in Chinese
[Paper]