Luke Yukun Jiang (江钰坤 in Chinese)

Biography

I am Luke, a Ph.D. student at CISPA Helmholtz Center for Information Security (Saarbrücken, Germany), advised by Prof. Michael Backes and Dr. Yang Zhang. I obtained my B.E. degree at Sichuan University (Chengdu, China) advised by Prof. Beibei Li in 2022.

Research Interests

• AI Security
• Privacy Preservation

News

• Mar. 2026: our preprint ‘‘Real Money, Fake Models: Deceptive Model Claims in Shadow APIs’’ is available [here]. It has been coveraged by [JIQIZHIXIN | Synced (Chinese)].
• Feb. 2026: our preprint ‘‘Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs’’ is available [here].
• Feb. 2026: our preprint ‘‘“Humans welcome to observe”: A First Look at the Agent Social Network Moltbook 🦞’’ is available [here]. It has been coveraged by multiple medias ([TechXplore] [AI Era (Chinese)]).
• Nov. 2025: our preprint ‘‘From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection’’ is available [here].
• Sep. 2025: our work ‘‘Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency’’ has been accepted by NeurIPS 2025. See you in San Diego.

Service

• PC Member: AAAI’26, SaTML’26
• Conference Reviewer: ICML’26, CVPR’26, ICLR’26, NeurIPS’25, ACL Rolling Review (ARR)
• Journal Reviewer: Transactions on Information Forensics & Security (T-IFS), Transactions on Dependable and Secure Computing (TDSC), Transactions on Intelligent Transportation Systems (T-ITS)

Working Experience

• Feb. 2022 - Aug. 2022, Research Intern at Tencent Cloud, advised by Dr. Yong Cheng

Preprints

• Yukun Jiang*, Yage Zhang*, Xinyue Shen*, Michael Backes, Yang Zhang: ‘‘“Humans welcome to observe”: A First Look at the Agent Social Network Moltbook.’’ [Website] [PDF] [Dataset] [arXiv] Media Coverage: [TechXplore] [AI Era (Chinese)]
• Yukun Jiang, Hai Huang, Mingjie Li, Yage Zhang, Michael Backes, Yang Zhang: ‘‘Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs.’’ [arXiv] [Code]
• Yage Zhang, Yukun Jiang, Zeyuan Chen, Michael Backes, Xinyue Shen, Yang Zhang: ‘‘Real Money, Fake Models: Deceptive Model Claims in Shadow APIs.’’ [arXiv] Media Coverage: [JIQIZHIXIN | Synced (Chinese)]).
• Mengfei Liang, Yiting Qu, Yukun Jiang, Michael Backes, Yang Zhang: ‘‘From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection.’’ [arXiv]

Publications

• Yukun Jiang, Mingjie Li, Michael Backes, Yang Zhang: ‘‘Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency.’’ The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025) [PDF] [Link] [Code]
• Yukun Jiang, Zheng Li, Xinyue Shen, Yugeng Liu, Michael Backes, Yang Zhang: ‘‘ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities.’’ The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) [PDF] [Link] [Code]
• Yukun Jiang, Xinyue Shen, Rui Wen, Zeyang Sha, Junjie Chu, Yugeng Liu, Michael Backes, Yang Zhang: ‘‘Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming.’’ International AAAI Conference on Web and Social Media (ICWSM 2024) [PDF] [Link]
• Yukun Jiang, Xiaoyu Cao, Hao Chen, Neil Gong: ‘‘FedER: Communication-Efficient Byzantine-Robust Federated Learning.’’ International Conference on Learning Representations 2022 Workshop on Socially Responsible Machine Learning (ICLR 2022-SRML) [PDF]
• Beibei Li, Yukun Jiang, Qingqi Pei, Tao Li, Liang Liu, Rongxing Lu: ‘‘FEEL: Federated End-to-End Learning with Non-IID Data for Vehicular Ad Hoc Networks.’’ IEEE Transactions on Intelligent Transportation Systems T-ITS (T-ITS) [Link]
• Beibei Li, Yukun Jiang, Wenbin Sun, Weina Niu, Peiran Wang: ‘‘FedVANET: Efficient Federated Learning with Non-IID Data for Vehicular Ad Hoc Networks.’’ Proceedings of IEEE Global Communications Conference 2021 (GLOBECOM 2021) [Link] [PDF]
• Beibei Li, Yaxin Shi, Yuqing Guo, Qinglei Kong, Yukun Jiang: ‘‘Incentive-Based Adaptive Federated Knowledge Distillation for Cross-Silo Applications.’’ Proceedings of IEEE International Conference on Computer Communications Workshops (INFOCOM 2022 WORKSHOPS) [PDF]
• Beibei Li, Peiran Wang, Hanyuan Huang, Shang Ma, Yukun Jiang: ‘‘FLPhish: Reputation-Based Phishing Byzantine Defense in Ensemble Federated Learning.’’ Proceedings of IEEE Symposium on Computers and Communications 2021 (ISCC 2021) Best Paper Award [Link] [PDF]

Awards

• Best Paper Award, ISCC 2021

---