English
刘晓明
研究领域或方向

大语言模型应用与安全、智能体任务规划与进化策略、时空数据挖掘、深度学习方法及其应用

工作简历

1.2024.04-至今,西安交通大学,网络空间安全学院,长聘副教授

2.2021.04-2024.03,西安交通大学,网络空间安全学院,副教授

3. 2019.04-2021.03,西安交通大学,网络空间安全学院,讲师/助理教授

科研项目

1.2025-2026,数字政府背景下的大语言模型生成内容(AIGC)监管与检测技术体系研究,西安交大-中国移动数字政府联合研究院2025年前沿探索研究基金项目(重点),主持

2.2025-2026,全媒体可信隐式水印嵌入与提取方法研究,OPPO公司,主持;

3.2023-2024,智慧水利安全监测平台(三期),中国联通甘肃省水利厅信息中心甘肃智慧水利项目,主持;

4.2023-2024,xxxx识别,电信十所,主持;

5.2023-2026,新型文本会话式电信网络诈骗犯罪动态检测方法研究,国家自然科学基金面上项目,主持;

6.2022-2024,xxxxxxx,重点研发子课题,主持;

7.2022-2023,智慧水利安全监测平台(二期),中国联通甘肃省水利厅信息中心甘肃智慧水利项目,主持;

8.2021-2023,面向小样本的图神经网络快速训练方法及应用研究,西安交通大学基本科研经费-学科交叉,主持;

9.2021-2022,智慧水利安全监测平台(一期),中国联通甘肃省水利厅信息中心甘肃智慧水利项目,主持;

10.2021-2022,基于短文本数据智能计算的网络舆情风险评估,传播内容认知国家重点实验室,参与;

11.2020-2021,多源文本内容感知驱动的个体/群体价值观和观点挖掘,传播内容认知国家重点实验室,主持;

12.2020-2023,全媒体可信共治众创模式与网络传播风控评估关键技术及核心系统,科技部重点研发计划课题,参与;

13.2020-2022,大规模多源异构社交网络数据驱动的异常群体识别,国家自然科学基金青年项目,主持;

学术科研

近三年代表性论文:

[1] Xiaoming Liu, Hang Pu, Zhuo Chen, Zhanwei Zhang, Yu Lan, and Chao Shen*. EvolGCN: A Co-evolutionary Graph Convolutional Network Model for Dynamically Spatio-Temporal Anomaly Event Inference. IEEE Transactions on Dependable and Secure Computing, 2025.(CCF A类期刊)

[2] Xiaoming Liu, Shaocong Wu, Zhaohan Zhang, and Chao Shen*. Unify Local and Global Information for Top-N Recommendation. SIGIR 2022.(CCF A类会议)

[3] Xiaoming Liu*, Zhaohan Zhang, Yichen Wang, Hang Pu, Yu Lan, and Chao Shen. Coco: Coherence-Enhanced Machine-Generated Text Detection Under Low Resource with Contrastive Learning. EMNLP 2023.(自然语言处理顶会、CCF B类会议)

[4] Chengzhengxu Li, Xiaoming Liu*, Zhaohan Zhang, Yichen Wang, Chen Liu, Yu Lan, and Chao Shen. Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models. NeurIPS 2024.(CCF A类会议)

[5] Shengchao Liu, Xiaoming Liu*, Yichen Wang, Zehua Cheng, Chengzhengxu Li, Zhaohan Zhang, Yu Lan, and Chao Shen. Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better. ACL 2024.(CCF A类会议)

[6] Xiaoming Liu*, Chen Liu, Zhaohan Zhang, Chengzhengxu Li, Longtian Wang, Yu Lan, and Chao Shen. StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation. EMNLP 2024.(自然语言处理顶会、CCF B类会议)

[7] Chengzhengxu Li, Xiaoming Liu*, Yichen Wang, Duyi Li, Yu Lan, and Chao Shen. Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning. AAAI 2024.(CCF A类会议)

[8] Xiaoming Liu, Zhanwei Zhang, Lingjuan Lyu, Zhaohan Zhang, Shuai Xiao, Chao Shen, and Philip S. Yu. Traffic Anomaly Prediction Based on Joint Static-Dynamic Spatio-Temporal Evolutionary Learning. IEEE Transactions on Knowledge and Data Engineering, 2023.(CCF A类期刊)

[9] Yichen Wang, Kevin Yang, Xiaoming Liu, and Dan Klein. Improving Pacing in Long-Form Story Planning. EMNLP 2023.(自然语言处理顶会、CCF B类会议)

[10] 刘晓明,张兆晗,杨晨阳,张宇辰,沈超*,周亚东,管晓宏. 在线社交网络文本内容对抗技术. 计算机学报, 2022.(CCF T1类期刊)

[11] Yuanfan Li, Zhaohan Zhang, Chengzhengxu Li, Chao Shen, and Xiaoming Liu*. Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training. ACL 2025.(CCF A类会议)

[12] Shengchao Liu, Xiaoming Liu*, Chengzhengxu Li, Zhaohan Zhang, Guoxin Ma, Yu Lan, and Shuai Xiao. Mgt-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment. AAAI 2026.(CCF A类会议)

联系方式

联系电话:

Email:xm.liu@xjtu.edu.cn

联系地址:彭康楼201房间

个人主页:https://gr.xjtu.edu.cn/web/xm.liu