网络安全态势感知，大模型/智能体安全

本人目前围绕大模型安全/大模型赋能网络安全态势感知等方向发表论文近50篇，部分代表论文列表如下：

[1] Hao Huang, Ruihua Zhou, JiaTang Luo, Yunpeng Li*, Yuling Liu. IACW: Intent-Aware Controllable Watermarking for Scalable Authorial Intent Attribution. Forty-third International Conference on Machine Learning (ICML 2026)，通讯作者，CCF-A

[2] Hao Huang, Yuling Liu, Yunpeng Li*, Ruihua Zhou, JiaTang Luo. Don’t Corrupt the Fact: A Trustworthy RAG Watermarking Framework based on Dual Factual Shield. (ACL 2026)，通讯作者，CCF-A

[3] Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao, Xiao Wang, Yuling Liu*. MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning. (ACL 2026)，协助指导，CCF-A

[4] Peizhuo Lv, Ruihua Zhou, Yunpeng Li, Ruigang Liang*, Xingshuo Han, XiaoFeng Wang, Wei Dong, Yuling Liu*. ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks. (ACL 2026)，协助指导，CCF-A

[5] Mingzhe Lu, Yiwen Wang, Yanbing Liu, Qi You, Chong Liu, Ruize Qin, Haoyu Dong, Wenyu Zhang, JiaRui Zhang, Yue Hu, Yunpeng Li*. LitVISTA: A Benchmark for Narrative Orchestration in Literary Text. (ACL 2026)，通讯作者，CCF-A

[6] Chenxu Niu, Jie Zhang, Yanbing Liu*, Yunpeng Li*, Jinta Weng, Yue Hu. RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models. (NeurIPS 2025)，通讯作者，CCF-A

[7] Xutong Wang, Yun Feng, Bingsheng Bi, Yaqin Cao, Ze Jin, Xinyu Liu, Yuling Liu, Yunpeng Li*. Not All Benignware Are Alike: Enhancing Clean-Label Attacks on Malware Classifiers. (WWW 2025)，通讯作者，CCF-A

[8] 黄昊，周瑞桦，罗家棠，李运鹏，马晓欢，刘玉岭. 从编译到反编译：基于源码级转换的高效水印去除方法。（中国科学：信息科学)，中文CCF-A

[9] Yunpeng Li, Yue Hu, Yajing Sun, Luxi Xing, Ping Guo, Yuqiang Xie, Wei Peng. Learning to know myself: A coarse-to-fine persona-aware training framework for personalized dialogue generation. (AAAI 2023)，第一作者，CCF-A

[10] Yunpeng Li, Yue Hu, Wei Peng, Yuqiang Xie. Think before you speak: Concept-guided explicit persona reasoning for personalized dialogue generation. (ICASSP 2023)，第一作者，CCF-B

[11] Jian Qin, Yunpeng Li, Tian Tian, Yan Zhu, Xuren Wang, Song Liu, Bo Jiang, Zhigang Lu. TrafficHTG: Revolutionizing Network Traffic Generation with Hierarchical Transformers. (ICASSP 2026)，第二作者，CCF-B

[12] Jian Qin, Xueying Han, Yunpeng Li, Dongqi Han, Wei Qiao, Xiaobo Yang, Zelin Cui, Bo Jiang, Zhigang Lu. TrafficMoE: Adaptive Multi-Perspective Feature Fusion for Enhancing Malicious Traffic General Detection Capability. (ICASSP 2026)，第三作者，CCF-B

[13] Jian Qin, Xueying Han, Yunpeng Li, Ding Wang, Susu Cui, Bo Jiang, Zhigang Lu, Baoxu Liu. GranulNet: A unified framework for traffic identification using multi-grained feature fusion. (Computer Security)，第三作者，CCF-B

[14] Yingchang Jiang, Hao Hu, Yunpeng Li, Feiyang Li, Changzhi Zhao, Canhua Chen, Yuling Liu. A zero-shot self-improving NER method for cyber threat intelligence via knowledge injection. (Cybersecurity)，第三作者，CCF-B

[15] Ping Guo, Yubing Ren, Yue Hu, Yanan Cao, Yunpeng Li, Heyan Huang. Steering large language models for cross-lingual information retrieval. (SIGIR 2024)，CCF-A

[16] Ping Guo, Yue Hu, Yanan Cao, Yubing Ren, Yunpeng Li, Heyan Huang. Query in your tongue: Reinforce large language models with retrievers for cross-lingual search generative experience. (WWW 2024)，CCF-A