|
个人信息Personal Information
副教授（特聘）
主要任职：副教授
其他联系方式Other Contact Information
邮箱 :
个人简介Personal Profile
姜文博目前是电子科技大学计算机科学与工程学院（网络空间安全学院）副教授。教育经历方面，本、硕、博均毕业于电子科技大学计算机科学与工程学院网络空间安全专业，硕士和博士期间导师为教育部“长江学者奖励计划”特聘教授、IEEE Fellow李洪伟教授。2021年至2022年间受国家留学基金委资助，前往新加坡南洋理工大学进行联合培养，联合培养期间导师为Tianwei Zhang教授。
学术研究方面，近年来一直从事人工智能安全相关研究，在国内外顶尖期刊和会议上发表了50余篇人工智能安全相关的学术论文，其中CCF-A类论文20余篇，包括计算机安全领域顶级会议CCS、USENIX Security、NDSS，人工智能领域顶级会议CVPR、ICML、NeurIPS、AAAI，计算机安全领域顶级期刊 TDSC、TIFS等。
科研项目方面，主持国家青年自然科学基金项目、国家博新计划、中国博士后面上基金、四川省青年自然科学基金、国家重点研发计划子课题等多项科研项目；参与主研国家重点研发计划，国家自然科学基金重点等多项科研项目。
学术获奖方面，博后期间入选国家2023年博士后创新人才支持计划，以通信作者身份发表的论文获得计算机安全领域顶级会议CCS2025的杰出论文奖（Distinguished Paper Award），获得2025国际大学生创新大赛省级金奖及银奖（指导教师），获2019年国家网络安全奖学金，获Distinguished reviewer of TIOT等奖项。
学术服务方面，担任Electronics期刊（JCR-Q2）的客座编辑; 担任多个顶级会议的领域主席/高级会议程序委员，包括ICLR（CCF-A）、NeurIPS（CCF-A）、ACL（CCF-A）、IJCAI（CCF-B）、ICASSP（CCF-B）、IJCNN（CCF-C）、BMCV（CCF-C）等; 还担任了多个国际会议的workshop主席。更多信息参见个人主页：https://wenbo-jiang.github.io/
欢迎对人工智能安全感兴趣的本科、研究生同学加入实验室（联系wenbo_jiang@uestc.edu.cn）
科研项目
1. 国家博士后创新计划“博新计划”，64万，2024.01至 2025.12,主持
2. 国家青年科学基金项目（C类）, 30万，2025.01至 2027.12,主持
3. 中国博士后面上项目, 8万，2025.01至 2026.12,主持
4. 四川省青年科学基金项目, 10万，2025.01至 2026.12,主持
5.国家重点研发计划子课题，智能机器人信息安全防护技术，48万，2025-01 至 2028.12,子课题负责人
6. 国家电网横向项目，敏感数据泄露行为感知技术有效性分析，35.5万，2026-01 至 2026.12, 主持
科研成果获奖
1. 论文通讯作者身份获2025 ACM SIGSAC Conference on Computer and Communications Security (CCS) Distinguished Paper Award （计算机安全领域四大顶级会议之一）
2. 入选2023年国家博新计划资助（全国仅500人入选）
3. 获得2025年国际大学生创新大赛省级金奖及银奖（指导教师）
4. 2019年获中国互联网发展基金会颁发的国家网络安全奖学金
5. 2023年获四川省优秀毕业生、电子科技大学优秀博士后、电子科技大学学术新秀、电子科技大学优秀毕业生、电子科技大学优秀博士论文
社会兼职
1. 客座编辑：Electronics (Special issue: Security and Privacy for AI)
2. 会议领域主席/高级会议程序委员：ICLR 2026（CCF-A），IJCAI 2026(CCF-B) ，ICASSP 2026 (CCF-B)，IJCNN 2025 (CCF-C)，BMCV 2025 (CCF-C)
3. 会议workshop主席：DLNN 2025, IEEE ICAIM 2026, MICCIS 2026, IEEE PRMVAI 2026
4. 会议审稿人/会议程序委员：ICML, KDD, ICCV, CVPR, ICLR, NeurIPS等
5. 期刊审稿人：TIFS, TDSC, TCSVT, TNNLS, TAI, TVT等
部分代表性论文
Wenbo Jiang, Hongwei Li, Jiaming He, Rui Zhang, Guowen Xu, Tianwei Zhang, Rongxing Lu. I2I Backdoor: Backdoor Attacks against Image-to-Image Tasks. IEEE Transactions on Dependable and Secure Computing(TDSC), 2025. （计算机安全领域顶级期刊，CCF-A）
Wenbo Jiang, Hongwei Li, Guowen Xu, Tianwei Zhang, "Color backdoor: a robust poisoning attack in color space", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June, 2023 （计算机视觉领域顶会，CCF-A）
Wenbo Jiang, Hongwei Li, Guowen Xu, Hao Ren, Haomiao Yang, Tianwei Zhang, Shui Yu, “Rethinking the Design of Backdoor Triggers and Adversarial Perturbations: A Color Space Perspective” in IEEE Transactions on Dependable and Secure Computing, 2024（计算机安全领域顶级期刊，CCF-A）
Wenbo Jiang, Hongwei Li, Guowen Xu, Tianwei Zhang and Rongxing Lu, "A comprehensive defense framework against model extraction attacks", in IEEE Transactions on Dependable and Secure Computing (TDSC), 2023（计算机安全领域顶级期刊，CCF-A）
Wenbo Jiang, Tianwei Zhang, Han Qiu, Hongwei Li and Guowen Xu，"Incremental learning, incremental backdoor threats", in IEEE Transactions on Dependable and Secure Computing (TDSC), 2022. （计算机安全领域顶级期刊，CCF-A）
Wenshu Fan, Minxing Zhang, Hongwei Li, Wenbo Jiang*, Hanxiao Chen, Xiangyu Yue, Michael Backes, Xiao Zhang, “DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy”, in Proceedings of ACM SIGSAC Conference on Computer and Communications Security (CCS), 2025（计算机安全领域顶级会议，CCF-A）
Jiaming He, Wenbo Jiang*, Guanyu Hou, Wenshu Fan, Rui Zhang and Hongwei Li. " Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models." Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA, February 25-March 4, 2025. （人工智能领域顶级会议，CCF-A）
Wenshu Fan, Hongwei Li, Wenbo Jiang*, Meng Hao, Shui Yu, Xiao Zhang, "Stealthy Targeted Backdoor Attacks against Image Captioning", IEEE Transactions on Information Forensics and Security, vol. 19, pp. 5655-5667, 2024, doi: 10.1109/TIFS.2024.3402179. （计算机安全领域顶级期刊，CCF-A）
Jiaming He, Guanyu Hou, Hongwei Li, Zhicong Huang, Kangjie Chen, Yi Yu, Wenbo Jiang*, Hongwei Li, Guowen Xu, Tianwei Zhang, "TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models", Conference on Computer Vision and Pattern Recognition (CVPR), 2026（计算机视觉领域顶会，CCF-A）
Qiyang Song, Qihang Zhou, Xiaoqi Jia, Zhenyu Song, Wenbo Jiang, Heqing Huang, Yong Liu, Dan Meng. vCause: Efficient and Verifiable Causality Analysis for Cloud-based Endpoint Auditing. The 35th USENIX Security Symposium, 2026（计算机安全领域顶级会议，CCF-A）
Rui Zhang, Hongwei Li, Rui Wen, Wenbo Jiang, et al. " Instruction backdoor attacks against customized LLMs", USENIX Security 2024（计算机安全领域顶级会议，CCF-A）
Rui Zhang, Yun Shen, Hongwei Li, Wenbo Jiang, Hanxiao Chen, Yuan Zhang, Guowen Xu, Yang Zhang. The Ripple Effect: On Unforeseen Complications of Backdoor Attacks. International Conference on Machine Learning (ICML), 2025.（人工智能领域顶级会议，CCF-A）
Shuai Yuan, Hongwei Li, Rui Zhang, Hangcheng Cao, Wenbo Jiang, Tao Ni, Wenshu Fan, Qingchuan Zhao, Guowen Xu. Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition. International Conference on Machine Learning (ICML), 2025. （人工智能领域顶级会议，CCF-A）
Kunlan Xiang, Haomiao Yang, Meng Hao, Shaofeng Li, Haoxin Wang, Zikang Ding, Wenbo Jiang, Tianwei Zhang. The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning. IEEE Transactions on Information Forensics and Security (TIFS), 2025. (计算机安全领域顶级期刊，CCF-A)
Shuai Yuan, Xingshuo Han, Hongwei Li, Guowen Xu, Wenbo Jiang, Tao Ni, Qingchuan Zhao, Yuguang Fang. The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition. The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025. （人工智能领域顶级会议，CCF-A）
Zihan Wang, Rui Zhang, Yu Liu, Wenshu Fan, Wenbo Jiang, Qingchuan Zhao, Hongwei Li, Guowen Xu*. MPMA: Preference Manipulation Attack Against Model Context Protocol. The Fortieth AAAI Conference on Artificial Intelligence (AAAI), 2026.（人工智能领域顶级会议，CCF-A）
Zihan Wang, Rui Zhang, Hongwei Li, Wenshu Fan, Wenbo Jiang, Qingchuan Zhao, Guowen Xu*. ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models. The Fortieth AAAI Conference on Artificial Intelligence (AAAI), 2026.（人工智能领域顶级会议，CCF-A）
Hanxiao Chen, Hongwei Li, Meng Hao, Pengzhi Xing, Jia Hu, Wenbo Jiang, Tianwei Zhang, and Guowen Xu. Conan: Secure and Reliable Machine Learning Inference against Malicious Service Providers. IEEE Transactions on Information Forensics and Security (TIFS), 2025. (计算机安全领域顶级期刊，CCF-A)
Xin Liu, Qiyang Song, Qihang Zhou, Haichao Du, Shaowen Xu, Wenbo Jiang, Weijuan Zhang, Xiaoqi Jia. Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models. The Fortieth AAAI Conference on Artificial Intelligence (AAAI), 2026（人工智能领域顶级会议，CCF-A）
Qianxin Xia, Zhiyong Shu, Wenbo Jiang, Jiawei Du, Jielei Wang, Guoming Lu. DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery. Conference on International Conference on Machine Learning (ICML) (CCF-A), 2026.
Ji Guo, Xiaolong Qin, Cencen Liu, Jielei Wang, Jierun Chen, Wenbo Jiang*. CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models. Conference on International Conference on Machine Learning (ICML) (CCF-A), 2026.
Tianxin Chen, Wenbo Jiang, Hongqiao Chen, Zhirun Zheng, Cheng Huang. Semantic-level Backdoor Attack against Text-to-Image Diffusion Models. Conference on International Conference on Machine Learning (ICML) (CCF-A), 2026.
Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang. The Art of (Mis) alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training. 2026 ACL Finding.
Rui Zhang, Zihan Wang, Tianli Yang, Wenbo Jiang, Qingchuan Zhao, Hongwei Li, Yang Liu, Guowen Xu. Hidden Tail: Adversarial Attack for Stealthy Resource Consumption against Vision-Language Models, in IEEE Transactions on Dependable and Secure Computing, 2026.
Cencen Liu, Dongyang Zhang, Wen Yin, Jielei Wang, Tianyu Li, Ji Guo, Wenbo Jiang, Guoqing Wang, Guoming Lu. AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution. Findings of Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
Yirui bai, qiyang song, qihang zhou, xin liu, Wenbo Jiang, haichao du, nan jiang, shaowen xu, xiaoqi jia. The Devil’s Whisper to Agents: Unveiling and Formalizing Training-Free Backdoor Attacks Across the MCP-Enabled Agent Execution Lifecycle, ACSAC 2027.
Jia Hu, Hongwei Li, Meng Hao, Hanxiao Chen, Pengzhi Xing, Wenbo Jiang, Dongxiao Liu, Haiyang Xue, Robert H. Deng. Vespa: Efficient Secure Aggregation with Integrity Defense under Server Privacy, NDSS 2027 (CCF-A).
Zihan Wang, Hongwei Li, Rui Zhang, Wenbo Jiang, Kangjie Chen, Tianwei Zhang, Qingchuan Zhao, Guowen Xu. BadLingual: Language-triggered anomalous behavior in multilingual foundation Large Language Models, Pattern Recognition, 2026.
Ji Guo, Yansong Lin, Man Jiang, Jielei Wang, Cong Chen, Wenbo Jiang, Hongwei Li. BadDenoise: Backdoor attacks on self-supervised image denoising, Pattern Recognition, 2026.
Ji Guo, Zhijing Wang, Wenbo Jiang*, Rui Zhang, Jian Xiong, Qiyang Song, Hao Wu, Yijing Liu. BiasAgent: Exploiting Agent Bias for Preference Manipulation Attacks on Model Context Protocol. IEEE Transactions on Cognitive Communications and Networking, 2026.
Qing Xie, Xiaoyang Ning, Jinyu Xu, Wenbo Jiang*, Mingxuan Yao, Jiachen Li, Yanchun Ma. Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features. IEEE TCSVT, 2026.
其他论文成果见 https://scholar.google.com/citations?user=OjHzvJkAAAAJ