Xiaohu Du

13 papers A* 2B 1Journal 6Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
SEAttack: A self-evolving jailbreak attack to induce toxic responses for non-toxic queries in large language models.
Inf. Process. Manag.
Huijun Liu, Shasha Li, Bin Ji, Xiaohu Du, Xiaopeng Li, Jun Ma, Jie Yu
2026 J jnl
Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats.
CoRR
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
2025 A* conf
Multi-Turn Jailbreaking Large Language Models via Attention Shifting.
AAAI
Xiaohu Du, Fan Mo, Ming Wen, Tu Gu, Huadi Zheng, Hai Jin, Jie Shi
2025 A* conf
Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations.
EMNLP
Yongkang Chen, Xiaohu Du, Xiaotian Zou, Chongyang Zhao, Huan Deng, Hu Li, Xiaohui Kuang
2025 J jnl
Statement-Level Adversarial Attack on Vulnerability Detection Models via Out-of-Distribution Features.
Proc. ACM Softw. Eng.
Xiaohu Du, Ming Wen, Haoyu Wang, Zichao Wei, Hai Jin
2025 J jnl
Two-stage landslide satellite image recognition in the southeastern tibet region based on Cascade R-CNN and SAM2.
Earth Sci. Informatics
Jian Zhang, Xiangyu Chen, Mingwei Yu, Yonggang Guo, Xiaohu Du
2024 — conf
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning.
ACL (Findings)
Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, Hai Jin
2024 J jnl
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning.
CoRR
Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, Hai Jin
2023 — conf
An Extensive Study on Adversarial Attack against Pre-trained Models of Code.
ESEC/SIGSOFT FSE
Xiaohu Du, Ming Wen, Zichao Wei, Shangwen Wang, Hai Jin
2023 J jnl
An Extensive Study on Adversarial Attack against Pre-trained Models of Code.
CoRR
Xiaohu Du, Ming Wen, Zichao Wei, Shangwen Wang, Hai Jin
2023 — conf
Understanding the Bug Characteristics and Fix Strategies of Federated Learning Systems.
ESEC/SIGSOFT FSE
Xiaohu Du, Xiao Chen, Jialun Cao, Ming Wen, Shing-Chi Cheung, Hai Jin
2021 B conf
Combating Word-level Adversarial Text with Robust Adversarial Training.
IJCNN
Xiaohu Du, Jie Yu, Shasha Li, Zibo Yi, Hai Liu, Jun Ma
2020 — conf
Generating More Effective and Imperceptible Adversarial Text Examples for Sentiment Classification.
ICAIS (1)
Xiaohu Du, Zibo Yi, Shasha Li, Jun Ma, Jie Yu, Yusong Tan, Qinbo Wu