丛天硕，山东大学密码科学与工程学院研究员/院长助理，山东省智能安全重点实验室副主任，入选2026年度中国电子学会青年人才托举工程计划，齐鲁青年学者。
清华大学学士/博士/博士后，导师为王小云院士。德国CISPA亥姆霍兹信息安全中心访问博士生，导师为张阳研究员。科技创新2030国家网络空间安全国家科技重大专项课题负责人、主持国家自然科学基金青年科学基金项目(C类)、“中国联通-山东大学”联合创新中心联合研发项目。研究成果发表于IEEE S&P、ACM CCS、USENIX Security、NDSS等信息安全与人工智能顶会顶刊20余篇。获中国密码学会优秀博士论文，LAMPS’24 Best Paper Award，NDSS 2025 Distinguished Poster Award等荣誉。CCF网络与系统安全专业委员会执行委员，CCSS智能化网络安全专业委员会委员，USENIX Security、RAID、EuroS&P等程序委员会委员，ICLR、NeurIPS领域主席，NDSS分会场主席。
更多详情请参考个人主页：https://tianshuocong.github.io/
课题组主要开展“密码学 x 人工智能安全”研究：
可证明安全的人工智能生成内容溯源技术
大模型安全对齐鲁棒性分析理论
基于隐私计算技术的大模型隐私防护体系
课题组常年招收博士后，博士生，硕士生，研究助理（本科2年级起，可远程），工程师，欢迎邮件咨询！
[完整列表见 Google Scholar]
Tianshuo Cong, Xinlei He, Yun Shen, and Yang Zhang. Test-time Poisoning Attacks Against Test-time Adaptation Models. S&P 2024 (CCF-A, 安全四大).
Tianshuo Cong, Xinlei He, and Yang Zhang. SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders. CCS 2022 (CCF-A, 安全四大).
Tianshuo Cong, Pei Li, Haojie Wu, Jinyuan Liu, Tairong Huang, Guoyan Zhang, and Anyu Wang. Rethinking the Stealthiness of Cryptographically Undetectable Backdoors in Practical RFF Learning. KDD 2026 (CCF-A).
Tianshuo Cong, Delong Ran, Zesen Liu, Xinlei He, Jinyuan Liu, Yichen Gong, Qi Li, Anyu Wang, and Xiaoyun Wang. Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging. CCS-LAMPS 2024 (Best Paper Award).
Delong Ran, Jinyuan Liu, Yichen Gong, Jingyi Zheng, Xinlei He, Tianshuo Cong*, and Anyu Wang. JailbreakEval: An Integrated Safety Evaluator Toolkit for Assessing Jailbreaks Against Large Language Models. NDSS-Poster 2025 (Distinguished Poster Award).
Yule Liu, Heyi Zhang, Jingyi Zheng, Zhen Sun, Zifan Peng, Jiaheng Wei, Tianshuo Cong, Yilong Yang, and Xinlei He. Auditing Data Membership in Reinforcement Learning With Verifiable Rewards. NDSS 2027 (CCF-A, 安全四大).
Qihang Cen, Tianshuo Cong, Da Song, Xinlei He, Jiaxing Song, Ke Xu, and Qi Li. PriMobiBench: Characterizing Visual Privacy Leakage in VLM-Driven Mobile GUI Agents. CCS 2026 (CCF-A, 安全四大).
Pei Li, Sihan Chen, Delong Ran, and Tianshuo Cong*. FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection. KDD 2026 (CCF-A).
Tianrui Wang, Anyu Wang*, Tianshuo Cong*, Delong Ran, Jinyuan Liu, and Xiaoyun Wang. Cryptanalysis of LDPC-based Pseudorandom Error-Correcting Codes. USENIX Security 2026 (CCF-A, 安全四大).
Jinyuan Liu, Tianshuo Cong*, Pei Li, Tianrui Wang, Xinlei He, Anyu Wang, and Xiaoyun Wang. Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor. USENIX Security 2026 (CCF-A, 安全四大).
Yugeng Liu, Tianshuo Cong*, Zhengyu Zhao, Michael Backes, Yun Shen, Yang Zhang. Robustness Over Time: Understanding Adversarial Examples’ Effectiveness on Longitudinal Versions of Large Language Models. IEEE Transactions on Information Forensics & Security (TIFS) 2026 (CCF-A).
Yu Zhang, Miao Chen, Xinlei He, Tianshuo Cong, Ke Xu, Qi Li. Covert Knowledge Poisoning Attacks in Retrieval-Augmented Code Generation. IEEE Transactions on Dependable and Secure Computing (TDSC) 2026 (CCF-A).
Chuanchao Zang, Xiangtao Meng, Wenyu Chen, Tianshuo Cong, Yaxing Zha, Dong Qi, Zheng Li, and Shanqing Guo. ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space. NeurIPS 2025 (CCF-A).
Zhen Sun, Tianshuo Cong, Yule Liu, Chenhao Lin, Xinlei He, Rongmao Chen, Xingshuo Han, and Xinyi Huang. PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning. S&P 2025 (CCF-A, 安全四大).
Lijin Wang, Jingjing Wang, Tianshuo Cong*, Xinlei He*, Zhan Qin, and Xinyi Huang. From Purity to Peril: Backdooring Merged Models From “Harmless” Benign Components. USENIX Security 2025 (CCF-A, 安全四大).
Yichen Gong, Delong Ran, Xinlei He, Tianshuo Cong*, Anyu Wang*, and Xiaoyun Wang. Safety Misalignment Against Large Language Models. NDSS 2025 (CCF-A, 安全四大).
Yichen Gong, Delong Ran, Jinyuan Liu, Conglei Wang, Tianshuo Cong*, Anyu Wang*, Sisi Duan, and Xiaoyun Wang. FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts. AAAI 2025 (CCF-A).
Jingyi Zheng, Tianyi Hu, Tianshuo Cong, and Xinlei He. CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers. AAAI 2025 (CCF-A).
中国电子学会青年人才托举工程（2026）
中国密码学会优秀博士论文（2023）
山东大学齐鲁青年学者（2025）
清华大学水木学者（2023）
全国密码算法设计竞赛(分组算法)二等奖（2021）
KDD 2026 Best Reviewer
KDD 2025 Excellent Reviewer
ICLR 2025 Notable Reviewer
NDSS 2025 Distinguished Poster Award
LAMPS@CCS 2024 Best Paper Award
主持，科技创新2030国家网络空间安全国家科技重大专项课题, 课题负责人, 2026.5-2029.4
主持，国家自然科学基金青年基金项目(C类), 项目负责人, 2025.1-2027.12
主持，山东省重点研发计划课题, 课题负责人, 2026.7-2029.6
主持，“中国联通-山东大学”联合研发项目，项目负责人, 2026.1-2027.12
参与，国家重点研发计划，课题骨干，2024.12-2029.11
参与，国家自然科学基金面上项目，2021.1-2024.12
中国网络空间安全学会 (CCSS) 第一届智能化网络安全专业委员会委员
中国计算机学会 (CCF) 网络与系统安全专业委员会首批执行委员
Area Chair: ICLR 2026, NeurIPS 2026
PC Member: USENIX Security 2026/2027, IEEE EuroS&P 2025/2026, ACSAC 2024/2025, PETS 2025/2026, IEEE SatML 2027 等
Session Chair: NDSS 2025
