
牛温佳
博士 、教授 、博导,中国人民公安大学客座教授
博士 、教授 、博导,中国人民公安大学客座教授
办公电话: | 电子邮件: niuwj@bjtu.edu.cn |
通讯地址:海淀区上园村3号北京交通大学 | 邮编:100044 |
牛温佳,北京交通大学网络空间安全学院教授,博士生导师,人工智能安全研究中心主任。中国人民公安大学客座教授。本科毕业于北京交通大学计算机应用专业,博士毕业于中科院计算所计算机软件与理论专业(导师:史忠植),国家公派美国加州大学尔湾分校与新加坡国立大学高级研究学者。担任国家某重点领域总师组专家和蓝队专家。担任 CCF 杰出会员、IEEE 高级会员、CAAI 知识工程与分布智能、智能信息网络、心智计算专委会委员、CCF 智能汽车专委会执委、CAA 混合智能专委会执委。主持科技部重点研发计划课题、基金委应急和面上项目、某科技委应用推进计划等国家级项目。第一作者出版专著2本,第一或通信作者发表论文超百篇,包含IEEE汇刊、CCF中文T1期刊、CCF A类会议等。获得某部系统应用证明和重要服务保障表扬信,获批保密行标1项《互联网某检测器技术要求》。在鹏城实验室面向北京冬奥会、冬残奥会的安全演练活动中,带队以第一名成绩获一等奖。在百度安全BCTF和加州大学尔湾分校(UCI)联合承办的DEF CON 29 和DEF CON 30 自动驾驶安全挑战赛(AutoDriving CTF)中,带队连续两年获得第二名。带队参与海关2023年网络攻防演习专项工作,获得全国海关信息中心的感谢信。
研究方向:人工智能应用与安全、强化学习应用与安全、自动驾驶与车联网安全、知识图谱应用与安全、大模型安全等(详见实验室团队主页: THETA Lab )
本年度拟计划招收2026级推免硕士生2~3名,2026级博士生1~2名,如有意愿请与我邮件联系。
欢迎推免/统考的硕士研究生、工学/工程博士研究生与我邮件联系,有信必回:)
2001-2005,北京交通大学,计算机科学与技术,学士
2005-2010,中科院计算所,计算机软件与理论,博士(导师史忠植,中国人工智能学会会士、中国计算机学会会士)
2018-2019,美国加州大学尔湾分校研究学者 (导师Ramesh Jain,Fellow of ACM, IEEE, AAAS, IAPR, AAAI, and SPIE)
2024-2025,新加坡国立大学高级研究学者 (导师Jinsong Dong, Fellow of Institute of Engineers Australia)
2010.7-2013.3, 中科院声学研究所高性能网络实验室,助理研究员;
2013.4-2017.3, 中科院信息工程研究所,副研究员,硕导;
2017.4至今, 北京交通大学计算机与信息技术学院,教授,博导;
所主持的主要项目:
(1) 国家重点研发计划课题1项(2020YFB1005604,202万/1600万)
(2) 专项项目-应用推进计划课题1项(173万/4700万)
(3) 专项项目-基础预研项目(60万/400万)
(4) 石家庄揭榜挂帅项目(100万/500万)
(5) 国家自然科学基金面上项目2项(20万/50万,60万/60万)和青年基金1项(24万/24万)
(6) 国家自然科学基金应急管理项目1项(M1552006,80万/80万)
(7) 国家科学技术奖励办公室项目1项(2016JLB016,46.4万/46.4万)
(8) 专项项目-重点实验室基金课题1项(614200103011711,16万/16万)
所参与的重要项目:
(1) 中科院战略性先导科技专项(XDA06030200)(1343万)
研究生课程:
(1)《网络空间安全态势感知》(博)
(2)《人工智能安全》(硕)
本科生课程:
(1)《安全通论》
(2)《金融数据安全》
(3)《信息安全专业实践与训练》
人才培养:
指导硕博毕业生超50余人,就业单位(顺序不分先后)包括:中央网信办、国铁集团、字节跳动、阿里巴巴、IBM、微软、蚂蚁金服、京东、美团、用友、陌陌、国家互联网应急中心、北京朝阳区城建局、中国联通、中国移动、农业银行、民生银行、华夏银行、中科院信工所、北京交通大学、北京师范大学信息中心等。
近5年代表性论文如下:
Yunzhe Tian, Yike Li, Kang Chen, Zhenguo Zhang, Endong Tong, Jiqiang Liu, Fangyun Qin, Zheng Zheng, Wenjia Niu. “Towards Label-Efficient Deep Learning-based Aging-related Bug Prediction with Spiking Convolutional Neural Networks.” IEEE Transactions on Emerging Topics in Computing (2025). (IEEE Trans, SCI中科院2区)
徐冬月;田蕴哲;陈康;李轶珂;吴亚伦;童恩栋;牛温佳;刘吉强;史忠植. “面向信号调制识别的对抗攻击与防御综述”. 计算机研究与发展, 2025. (CCF中文T1类)
Ziyan Qiao, Yingxiao Xiang, Thar Baker, Gang Li, Yalun Wu, Endong Tong, Shuanghe Peng, Ye Zhu, Dongwei Xu, and Wenjia Niu. “Reinforcement Learning-based Security Enhancement for Controlled Optimization of Phases in Intelligent Traffic Signal System.” IEEE Transactions on Industrial Cyber-Physical Systems (2024). (IEEE Trans)
Yalun Wu†, Yingxiao Xiang†, Thar Baker, Endong Tong, Ye Zhu, Xiaoshu Cui, Zhenguo Zhang, Zhen Han, Jiqiang Liu, Wenjia Niu*. “Collaborative Attack Sequence Generation Model Based on Multi-Agent Reinforcement Learning for Intelligent Traffic Signal System.” International Journal of Intelligent Systems, 2024. (SCI中科院2区, CCF-C期刊)
Xiangyu Shi, Dianjing Cheng, Xingyu Wu, Ping Ye, Jingqi Jia, Jiqiang Liu, and Wenjia Niu. “ECG Signal Classification with a Multi-stage Model Integrating CNN, SNN, and ResNet.” International Conference on Advanced Data Mining and Applications, pp. 361-372. Singapore: Springer Nature Singapore, 2024. (CCF-C会议)
Yalun Wu, Qiong Li, Yingxiao Xiang, Jinkai Zheng, Xingyu Wu, Zhen Han, Jiqiang Liu, and Wenjia Niu. “Nightfall Deception: A Novel Backdoor Attack on Traffic Sign Recognition Models via Low-Light Data Manipulation.” International Conference on Advanced Data Mining and Applications, pp. 433-445. Singapore: Springer Nature Singapore, 2024. (CCF-C会议)
Yuanwan Chen, Yalun Wu, Xiaoshu Cui, Qiong Li, Jiqiang Liu, and Wenjia Niu. “Reflective Adversarial Attacks against Pedestrian Detection Systems for Vehicles at Night.” Symmetry 16, no. 10 (2024): 1262. (SCI中科院3区)
Xiaoshu Cui, Yalun Wu, Yanfeng Gu, Qiong Li, Endong Tong, Jiqiang Liu, and Wenjia Niu. “Lurking in the shadows: Imperceptible shadow black-box attacks against lane detection models.” International Conference on Knowledge Science, Engineering and Management, pp. 220-232. Singapore: Springer Nature Singapore, 2024. (CCF-C会议)
Jiayin Song, Yike Li, Yunzhe Tian, Xingyu Wu, Qiong Li, Endong Tong, Wenjia Niu, Zhenguo Zhang, and Jiqiang Liu. “Knowledge-Driven Backdoor Removal in Deep Neural Networks via Reinforcement Learning.” International Conference on Knowledge Science, Engineering and Management, pp. 336-348. Singapore: Springer Nature Singapore, 2024. (CCF-C会议)
Yunzhe Tian, Dongyue Xu, Endong Tong, Rui Sun, Kang Chen, Yike Li, Thar Baker, Wenjia Niu, and Jiqiang Liu. “Toward Learning Model-Agnostic Explanations for Deep Learning-Based Signal Modulation Classifiers.” IEEE Transactions on Reliability (2024). (IEEE Trans, SCI中科院2区, CCF-C期刊)
Yalun Wu, Yingxiao Xiang, Endong Tong, Yuqi Ye, Zhibo Cui, Yunzhe Tian, Lejun Zhang, Jiqiang Liu, Zhen Han. Wenjia Niu. Improving the Robustness of Pedestrian Detection in Autonomous Driving with Generative Data Augmentation. IEEE Network, 2024 (early access). (SCI中科院2区, 影响因子: 9.3)
Yike Li, Yunzhe Tian, Endong Tong, Wenjia Niu, and Jiqiang Liu. “Robust Reinforcement Learning via Progressive Task Sequence.” nternational Joint Conference on Artificial Intelligence (IJCAI-23).(CCF-A会议)
王硕汝, 牛温佳, 童恩栋, 陈彤, 李赫, 田蕴哲, 刘吉强, 韩臻, 李浥东: 强化学习离线策略评估研究综述, 计算机学报, 2021 (CCF-A中文期刊)
相迎宵, 李轶珂, 刘吉强, 王潇瑾, 陈彤, 童恩栋, 牛温佳, 韩臻: 面向降频污染攻击的智能交通拥堵态势量化分析, 软件学报, 2021. (CCF-A中文期刊)
Yike Li, Yunzhe Tian, Endong Tong, Wenjia Niu, Yingxiao Xiang, Tong Chen, Yalun Wu, Jiqiang Liu. Curricular Robust Reinforcement Learning via GAN-based Perturbation through Continuously Scheduled Task. Tsinghua Science and Technology, 2022, 28(1): 27-38. (SCI中科院1区)
Yike Li, Wenjia Niu, Yunzhe Tian, Tong Chen, Zhiqiang Xie, Yalun Wu, Yingxiao Xiang, Endong Tong, Thar Baker, Jiqiang Liu: Multi-Agent Reinforcement Learning-based Signal Planning for Resisting Congestion Attack in Green Transportation[J]. IEEE Transactions on Green Communications and Networking, 2022. (IEEE Trans, SCI中科院2区)
Tong Chen, Jiqiang Liu, Baker Thar, Yalun Wu, Yingxiao Xiang, Yike Li, Wenjia Niu, Endong Tong. A Mutual Information-based Assessment of Reverse Engineering on Rewards of Reinforcement Learning. IEEE Transactions on Artificial Intelligence, 2022 (early access). (IEEE Trans)
Endong Tong, Wenjia Niu, JiqiangLiu: A missing QoS prediction approach via time-aware collaborative filtering[J]. IEEE Transactions on Services Computing, 2021. (中科院1区, IEEE Trans, 影响因子:11)
用户网络行为画像——大数据中的用户网络行为画像分析与内容推荐应用,牛温佳、刘吉强、石川等,电子工业出版社(ISBN9787121280702),2016.3。
在标准方面,获保密行标1项
应用推进某项目总师组专家,某人才计划评审专家。
中国人民公安大学客座教授