陈平，青年研究员，博士生导师。2012年博士毕业于南京大学计算机软件与理论专业，美国普渡大学计算机专业的联合培养博士（2010-2011）。美国宾州州立大学的博士后研究员（2014-2018）。国家级青年人才（2024年），上海领军人才（2021年）。发表国际会议期刊论文100+，包括NDSS，CCS，USENIX Security，TIFS，TDSC，Automatica，CVPR，ICML，ACL等。承担国家重点研发课题，国家社科重大课题，省部级项目等多项科研任务，中美专利共40余项，著书3本，获得省部级以上科技奖励2项。应邀担任多个CCF-A类国际顶级会议的程序委员，如CCS、NeurIPS、ACM MM、AAAI等，担任MPDI Mathematics，CyberSecurity，网络安全学报等期刊的客座编辑(Guest Editor)。
个人主页
研究方向
内生安全，智能车安全，AI安全
联系方式
邮箱：pchen@fudan.edu.cn
办公室：复旦大学邯郸校区邯郸路220号科学楼523室
近5年代表性论文
(1) Xu Haowen, Tan Xue, Ma Lei, and Zhang Zhihao, Wang Chao, Wang Qingze, Ping Chen*, Dai Jun, Sun Xiaoyan. When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems. ICML, 2026 CCF-A
(2) Xue Tan, Yi Zheng, Huo Chang, and Yunruo Zhang, Liu Yu, Luan Hao, Yu Zhuyang, Dai Jun, Sun Xiaoyan, Ping Chen*. PRA-RAG:Provably Robust Aggregation in Retrieval-Augmented Generation against Retieval Corruption. ACL 2026 CCF-A.
(3) Xue Tan, Yi Zheng, Yunruo Zhang, and Yiran Chen, Ping Chen*, Xiangyang Xue. RAG Sensitive Information Protection via Anti-Mapping Representation Perturbation. Journal of Computer Research and Development. 2026. CCFT1
(4) Xie Yuchong, Zhang KaiKai, Liu Yu, and Yang Rundong, Ping Chen, Wang Shuai, She Dongdong. RandSet:Randomized Corpus Reduction for Fuzzing Seed Scheduling. OOPSLA, 2026 CCF-A.
(5) Tan Xue, Luan Hao, Luo Mingyu, and Yu Zhuyang, Dai Jun, Sun Xiaoyan, Ping Chen*. Was my data used for training? Membership Inference in Open-source LLMs via Neural Actiivations. NDSS 2026 CCF-A.
(6) Luan Hao, Tan Xue, Li Zhiheng, and Dai Jun, Sun Xiaoyan, Ping Chen*. Dataset Reduction and Watermark Removal via Self-supervised Learning for Model Extraction Attack. NDSS 2026 CCF-A
(7) Yu Liu and Ping Chen*. Measurement of Intrinsic Safety Resilience in Perceived Decision Systems. Science China Technological Sciences 2025. CCFT1.
(8) Yin Cai, Zhouhong Gu, Zhaohan Du, Zheyu Ye, Shaosheng Cao, Yiqian Xu, Hongwei Feng, Ping Chen*. MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments. ACL 2025. CCF-A.
(9) Lingyun Zhang, Yu Xie, Yanwei Fu, and Ping Chen.Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization. CVPR 2025. CCF-A.
(10) Lan Zhang, Peng Liu, Yoon-Ho Choi, and Ping Chen. Semantics-Preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection. TDSC 2022. CCF-A
(11) Zhisheng Hu, Ping Chen*, Minghui Zhu, and Peng Liu. A Co-design Adaptive Defense Scheme with Bounded Security Damages Against Heartbleed-like Attacks. TIFS 2021. CCF-A
相关代表性著作
(1) Zhisheng Hu，Ping Chen，Minghui Zhu，Liu Peng；Reinforcement Learning for Adaptive Cyber Defense against Zero-Day Attacks， In S. Jajodia, G. Cybenko, P. Liu, C. Wang, and M. Wellman (Eds.), Adversarial and Uncertain Reasoning for Adaptive Cyber Defense, Springer 2019.
(2) Ping Chen*; Zhisheng Hu; Jun Xu; Minghui Zhu; Rob Erbacher; SushilJajodia; Liu Peng; MTD Techniques for Memory Protection against Zero-Day Attacks, In S. Jajodia, G. Cybenko, P. Liu, C. Wang, and M. Wellman (Eds.), Adversarial and Uncertain Reasoning for Adaptive Cyber Defense, Springer 2019.
教学
本科：走近人工智能（AIB110003）2024-2026
本科：信息论、控制论、系统论基础（AIE631001）2024-2026
