Biography 个人简介

Ph.D., Assistant Researcher and Master's Supervisor at the School of Computer Science (School of Cybersecurity), Shanghai Jiao Tong University. Joined the Laboratory of Cryptography and Computer Security (LoCCS) in October 2024. Research focuses on trustworthy AI and the security/privacy of AI models, including security assessment of deep learning applications and tampering detection of AI models in cloud environments.

In AI security, published 10+ papers in top venues including IEEE S&P, ACM CCS, NDSS, USENIX Security, CVPR, and ICML, with 8 as first or corresponding author. Serves on the editorial board of IEEE TII, program committee for IEEE Euro S&P, PAKDD, IEEE HPCC, and reviewer for IEEE TIFS, IEEE TDSC, ICLR, IJCAI, ACM MM, and the Chinese Journal of Computers.

PI on five projects, including the NSFC Young Scientists Fund (Category C) and the Shanghai Natural Science Foundation Young Scientist Project; core member on national/provincial projects such as the National Key R&D Program, the Yangtze River Delta S&T Innovation Community Joint Research Program, and NSFC Key Projects. Co-led the team to win the 2025 Challenge Cup "Jiebang Guashuai" AI main track champion (First Prize) and the 2024 Global AI LLM Attack & Defense Challenge Outstanding Solution Award (one of two worldwide). Research outcomes were selected for the National Disruptive Technology Excellence Award and the World AI Conference "Top 10 Global AI for Sustainable Development Outstanding Cases."

Our team is dedicated to building secure, trustworthy, and verifiable AI models for critical application scenarios. We welcome collaboration and inquiries.

博士，上海交通大学计算机学院（网络空间安全学院）助理研究员，硕士生导师。2024年10月加入上海交通大学网络空间安全学院密码与计算机安全（LoCCS）实验室，主要研究方向为可信人工智能和人工智能模型的安全与隐私保护，包括深度学习应用的安全性评估及云环境下人工智能模型篡改检测等领域。

在人工智能安全方面，在包括IEEE S&P、ACM CCS、NDSS、USENIX Security、CVPR、ICML在内的信息安全、人工智能等领域知名学术会议和期刊上发表十余篇论文，其中以第一作者/通讯身份发表8篇。担任IEEE TII编委，IEEE Euro S&P、PAKDD、IEEE HPCC等会议PC成员，及IEEE TIFS、IEEE TDSC、ICLR、IJCAI、ACM MM、计算机学报等知名会议与期刊的审稿人。

主持国自然青年科学基金项目(C类)、上海市自然科学基金青年项目等项目5项，课题骨干身份参与国家重点研发计划、长三角科技创新共同体联合攻关专项和国家自然基金重点项目等国家省部级项目/课题。共同带队斩获2025年挑战杯“揭榜挂帅”人工智能领域主擂台赛擂主（特等奖第一名）、2024全球AI大模型攻防挑战赛杰出方案奖（全球唯二）。研究成果入选全国颠覆性技术优胜奖和世界人工智能大会“全球人工智能赋能可持续发展十大卓越案例”。

目前团队致力于面向重要应用场景构筑安全、可信和可验证的人工智能模型，欢迎感兴趣的老师和同学们联系交流！

Research Interests

研究兴趣

Trustworthy AI AI Security & Privacy
可信人工智能 人工智能安全与隐私
Teaching 教授课程
  • NIS4301: Theory and Application of Information Content Security - Spring 2025
  • NIS4301: 信息内容安全的理论与应用 - 2025春
Selected Publications 代表性论文
Visit my Google Scholar profile for full publications →
访问我的Google Scholar主页查看完整论文列表 →

* Corresponding Author, # Co-first Author

* 通讯作者, # 共同第一作者

Feature-Indistinguishable Attack to Circumvent Trapdoor-Enabled Defense Chaoxiang He, Bin Benjamin Zhu, Xiaojing Ma, Hai Jin, Shengshan Hu
ACM CCS 2021 CCF-A, top-tier security CCF-A, 安全四大
DorPatch: Distributed and Occlusion-Robust Adversarial Patch to Evade Certifiable Defenses Chaoxiang He, Xiaojing Ma, Bin Benjamin Zhu, Yimiao Zeng, Xiaofan Bai, Hai Jin, Dongmei Zhang
NDSS 2024 CCF-A, top-tier security CCF-A, 安全四大
Quantifying Large Language Model Attacks Through the Lens of Model Cognition Xiuming Liu#, Chaoxiang He#, Xuanran Yu, Jichen Chai, Feiyue Xu, Sheng Hang, Hanqing Hu, Bin Benjamin Zhu, Hongsheng Hu, Shi-Feng Sun, Dawu Gu, Shuo Wang*
USENIX Security 2026 CCF-A, top-tier security CCF-A, 安全四大
SoK: Robustness in Large Language Models against Jailbreak Attacks Feiyue Xu (co-advised PhD student)(共同指导的博士生), Hongsheng Hu, Chaoxiang He, Sheng Hang, Hanqing Hu, Xiuming Liu, Yubo Zhao, Zhengyan Zhou, Bin Benjamin Zhu, Shi-Feng Sun, Dawu Gu, Shuo Wang*
IEEE S&P 2026 CCF-A, top-tier security CCF-A, 安全四大
Enhancing Adversarial Transferability with Checkpoints of a Single Model’s Training Shixin Li#, Chaoxiang He#, Xiaojing Ma, Bin Benjamin Zhu, Shuo Wang, Hongsheng Hu, Dongmei Zhang, Linchen Yu
CVPR 2025 CCF-A, top-tier computer vision CCF-A, 计算机视觉顶会
Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models Xiaofan Bai#, Chaoxiang He#, Xiaojing Ma, Bin Benjamin Zhu, Hai Jin
ICML 2024 CCF-A, top-tier machine learning CCF-A, 机器学习顶会
Towards Stricter Black-box Integrity Verification of Deep Neural Network Models Chaoxiang He, Xiaofan Bai, Xiaojing Ma, Bin Benjamin Zhu, Pingyi Hu, Jiayun Fu, Hai Jin, Dongmei Zhang
ACM MM 2024 CCF-A, top-tier multimedia CCF-A, 多媒体顶会
MysticMask: Adversarial Mask for Impersonation Attack Against Face Recognition Systems Chaoxiang He, Yimiao Zeng, Xiaojing Ma, Bin Benjamin Zhu, Zewei Li, Shixin Li, Hai Jin
IEEE ICME 2024 CCF-B, top-tier multimedia CCF-B, 多媒体顶会
Artificial intelligence security and privacy: a survey Xinlei He, Guowen Xu, Xingshuo Han, Qian Wang, Lingchen Zhao, Chao Shen, Chenhao Lin, Zhengyu Zhao, Qian Li, Le Yang, Shouling Ji, Shaofeng Li, Haojin Zhu, Zhibo Wang, Rui Zheng, Tianging Zhu, Qi Li, Chaoxiang He, Qifan Wang, Hongsheng Hu, Shuo Wang, Shi-Feng Sun, Hongwei Yao, Zhan Qin, Kai Chen, Yue Zhao, Hongwei Li, Xinyi Huang, Dengguo Feng
SCIENCE CHINA Information Sciences CCF-A, high-quality information science journal CCF-A, 信息类高质量期刊
Fine-Grained and Efficient Self-Unlearning with Layered Iteration Hongyi Lyu, Xuyun Zhang, Hongsheng Hu, Shuo Wang, Chaoxiang He, Lianyong Qi
IJCAI 2025 CCF-A, top-tier AI CCF-A, 人工智能顶会
BadFU: Backdoor Federated Learning Through Adversarial Machine Unlearning Bingguang Lu, Hongsheng Hu, Yuantian Miao, Shaleeza Sohail, Chaoxiang He, Shuo Wang, Xiao Chen
RAID 2025 CCF-B, top-tier security CCF-B, 安全顶会
RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models Pingyi Hu, Xiaofan Bai, Xiaojing Ma*, Chaoxiang He*, Dongmei Zhang, Bin Benjamin Zhu
EMNLP 2025 CCF-B, top-tier NLP CCF-B, 自然语言处理顶会
Funding 资助项目
  • National Natural Science Foundation of China, Young Scientists Fund (Category C)
    2026.01 - 2028.12, Ongoing, PI
  • Shanghai Municipal Science and Technology Commission, 2025 Basic Research Program "Natural Science Foundation" Young Scientist Project
    2025.05 - 2028.04, Ongoing, PI
  • Shanghai Municipal Science and Technology Commission, Shanghai Science and Technology Action Plan Project (Topic)
    2025.07 - 2027.06, Ongoing, PI
  • Shanghai Jiao Tong University – Ant Group Joint Research Center on "AI and Security", "Digital Security Innovation Lab" Collaboration
    2026.01 - 2026.12, Ongoing, PI
  • Shanghai Jiao Tong University, New Faculty Start-up Program (H2 2024)
    2024.10 - 2027.12, Ongoing, PI
  • Other major participating projects
    Core member in national and provincial projects such as the National Key R&D Program, the Yangtze River Delta S&T Innovation Community Joint Research Program, and NSFC Key Projects.
  • 国家自然科学基金委员会，青年科学基金项目(C类)
    2026.01 - 2028.12, 在研, 主持
  • 上海市科学技术委员会，2025年度基础研究计划“自然科学基金”项目青年项目
    2025.05 - 2028.04, 在研, 主持
  • 上海市科学技术委员会，上海市科技行动计划项目课题
    2025.07 - 2027.06, 在研, 主持
  • 上海交通大学-蚂蚁集团“人工智能与安全”联合研究中心，“数字安全创新实验室”合作项目
    2026.01 - 2026.12, 在研, 主持
  • 上海交通大学，2024年下半年度“新进青年教师启动计划”
    2024.10 - 2027.12, 在研, 主持
  • 其他主要参与项目
    课题骨干身份参与国家重点研发计划、长三角科技创新共同体联合攻关专项和国家自然基金重点项目等国家省部级项目/课题。
Honors & Awards 获奖信息
  • 19th "Challenge Cup" 2025 Youth Innovation "Jiebang Guashuai" AI main track champion (First Prize) - Advisor
  • 2024 Global AI LLM Attack & Defense Challenge Outstanding Solution Award (one of two worldwide) - Advisor
  • 2025 National Disruptive Technology Innovation Competition Excellence Award - Recipient
  • World AI Conference "Top 10 Global AI for Sustainable Development Outstanding Cases" - Selected research outcomes
  • 第十九届"挑战杯"竞赛2025年度中国青年科技创新"揭榜挂帅"擂台赛"人工智能领域"主擂台赛擂主 (特等奖第一名) - 指导老师
  • 2024全球AI大模型攻防挑战赛杰出方案奖 (全球唯二) - 指导老师
  • 2025全国颠覆性技术创新大赛优胜奖 - 获奖者
  • 世界人工智能大会“全球人工智能赋能可持续发展十大卓越案例” - 研究成果入选
Academic Services 学术服务
  • Editorial Board / AE: IEEE TII
  • PC Member: Euro S&P, PAKDD, IEEE HPCC
  • Reviewer: IEEE TIFS, IEEE TDSC, ICLR, IJCAI, ACM MM, Chinese Journal of Computers
  • Editorial Board / AE: IEEE TII
  • PC Member: Euro S&P, PAKDD, IEEE HPCC
  • Reviewer: IEEE TIFS, IEEE TDSC, ICLR, IJCAI, ACM MM, 计算机学报