Jiacheng Liang

About Me

I am a Ph.D. candidate in Computer Science at Stony Brook University, advised byProf. Ting Wang. My research focuses on LLM safety and trustworthy AI, with an emphasis on identifying security vulnerabilities and developing robust defenses.

My work has been published at top-tier venues including IEEE S&P, ACL, EMNLP, ICLR, and AsiaCCS. I have also interned at Amazon AGI (Nova Responsible AI), where I developed adaptive red-teaming methods for RLHF systems.

My research interests include LLM post-training and alignment, LLM agent safety, jailbreak and backdoor defense, MoE safety alignment, and RAG safety.

Recent Publications (Full List)

• ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
  Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Charith Peris
  Annual Meeting of the Association for Computational Linguistics (ACL 2026)

• AutoRAN: Weak-to-Strong Jailbreaking of Large Reasoning Models
  Jiacheng Liang, Tanqiu Jiang, Yuhui Wang, Rongyi Zhu, Fenglong Ma, Ting Wang
  Annual Meeting of the Association for Computational Linguistics (ACL 2026)

• GraphRAG under Fire
  Jiacheng Liang, Yuhui Wang, Changjiang Li, Rongyi Zhu, Tanqiu Jiang, Neil Gong, Ting Wang
  IEEE Symposium on Security and Privacy 2026 (IEEE S&P’26)

• RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
  Jiacheng Liang, Yuhui Wang, Tanqiu Jiang, Ting Wang
  

• WaterPark: A Robustness Assessment of Language Model Watermarking
  Jiacheng Liang, Zian Wang, Lauren Hong, Shouling Ji, Ting Wang
  Empirical Methods in Natural Language Processing(EMNLP’25)

• RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
  Tanqiu Jiang, Zian Wang, Jiacheng Liang, Changjiang Li, Yuhui Wang, Ting Wang
  International Conference on Learning Representations (ICLR’25)

• Model Extraction Attacks Revisited
  Jiacheng Liang, Ren Pang, Changjiang Li, Ting Wang
  Asia Conference on Computer and Communications Security (Asia CCS’24)

• Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
  Xiaoqun Liu*, Jiacheng Liang*, Luoxi Tang, Muchao Ye, Weicheng Ma, Zhaohan Xi
  Empirical Methods in Natural Language Processing(EMNLP’25)

Services

Program Committee/Reviewer

Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
Association for the Advancement of Artificial Intelligence (AAAI)
IEEE Transactions on Dependable and Secure Computing (TDSC)
IEEE Transactions on Information Forensics and Security (TIFS)
IEEE Internet of Things Journal
Transactions on Intelligent Systems and Technology (TIST)
Cybersecurity Springer

Internships

2025.05 - 2025.10, Applied Scientist Intern at Amazon AGI Foundation - Responsible AI, Amazon, Boston.
Advisor: Dr. Charith Peris, Dr. Yao Ma

Collaborators and Previous Advisors

Teammates at ALPS-Lab: Ren Pang (Amazon), Zhaohan Xi (Binghamton University), Changjiang Li, Tanqiu Jiang, Zian Wang, Yuhui Wang, Rongyi Zhu

Previous Collaborators: Bochuan Cao (PSU), Qihua Zhou (SZU), Yanjing Ren (CUHK), Guoli Wei (USTC), Zicong Hong (HKUST), Jun Pan (HKPolyU)

Previous Advisors: Jingwei Li (UESTC), Song Guo (HKUST), Songze Li (SEU, HKUST)

Powered by Jekyll and Minimal Light theme.