Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
NYU Tandon launches NSOC
Published:
NYU Tandon has launched the NYU Software Supply Chain Security Operations Center (NSOC), an NYU Center for Cybersecurity initiative that embeds master’s students in open-source communities for a year of hands-on supply-chain security work. Prof. Jiahao Yu co-founded NSOC with Justin Cappos, Andrew Nesbitt, and Vlad-Stefan Harbuz. The first cohort starts in January 2027. More at nsoc.engineering.nyu.edu.
Jiahao Yu joins NYU Abu Dhabi
Published:
Jiahao Yu will join the Department of Computer Engineering at New York University Abu Dhabi as a Tenure-Track Assistant Professor. The Secure Reasoning Lab is actively looking for self-motivated Ph.D. students and postdocs. See Join Us.
PatchAgent selected as a CSAW 2025 finalist
Published:
Our work PatchAgent was accepted as a CSAW 2025 finalist (Technical Impact Runner-up). We presented the work in New York City.
GPO covered by MIT Technology Review China
Published:
Our work GPO: Learning from Critical Steps to Improve LLM Reasoning was covered by MIT Technology Review China.
EntroPO ranks 1st on SWE-bench Lite (open-weight)
Published:
The official SWE-bench Verified and SWE-bench Lite open-weight leaderboards were updated. EntroPO ranks 1st on SWE-bench Lite and 5th on SWE-bench Verified, behind only models about 10× larger.
Soft-label toxicity work covered by MIT Technology Review China
Published:
Our work Soft-Label Integration for Robust Toxicity Classification was covered by MIT Technology Review China.
GPTFuzzer wins the Geekcon 2023 Breakthrough Award
Published:
Our GPTFuzzer work received the Geekcon 2023 Annual Themed Debate Breakthrough Award and was covered by SECGEEK.
BandFuzz wins first prize at SBFT 2024
Published:
BandFuzz won first prize in the SBFT fuzzing competition and was covered by McCormick School of Engineering News.
Custom GPT prompt-injection work covered by WIRED
Published:
Our prompt-injection study on custom GPTs was covered by WIRED.
portfolio
Portfolio item number 2
Short description of portfolio item number 2 
publications
AIRS: Explanation for Deep Reinforcement Learning based Security Applications
Published in USENIX Security Symposium 2023, 2023
Recommended citation: Jiahao Yu, Wenbo Guo, Qi Qin, Gang Wang, Ting Wang, Xinyu Xing. (2023). "AIRS: Explanation for Deep Reinforcement Learning based Security Applications." USENIX Security.
Download Paper
StateMask: Explaining Deep Reinforcement Learning through State Mask
Published in Neural Information Processing Systems (NeurIPS) 2023, 2023
Recommended citation: Zelei Cheng*, Xian Wu*, Jiahao Yu*, Wenhai Sun, Wenbo Guo, Xinyu Xing. (2023). "StateMask: Explaining Deep Reinforcement Learning through State Mask." NeurIPS.
Download Paper
BandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning
Published in ICSE Workshop on Search-Based and Fuzz Testing (SBFT) 2024, 2024
First prize at the SBFT 2024 Fuzzing Competition.
Recommended citation: Wenxuan Shi, Hongwei Li, Jiahao Yu, Wenbo Guo, Xinyu Xing. (2024). "BandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning." ICSE@SBFT.
Download Paper
Assessing Prompt Injection Risks in 200+ Custom GPTs
Published in ICLR Workshop on Secure and Trustworthy Large Language Models 2024, 2024
Featured in WIRED.
Recommended citation: Jiahao Yu, Yuhang Wu, Dong Shu, Mingyu Jin, Xinyu Xing. (2024). "Assessing Prompt Injection Risks in 200+ Custom GPTs." ICLR@SeT-LLM.
Download Paper
RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
Published in International Conference on Machine Learning (ICML) 2024, 2024
ICML 2024 Spotlight (top 3.5%).
Recommended citation: Zelei Cheng*, Xian Wu*, Jiahao Yu*, Sabrina Yang, Gang Wang, Xinyu Xing. (2024). "RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation." ICML Spotlight.
LLM-Fuzzer: Scaling Assessment of Large Language Model Jailbreaks
Published in USENIX Security Symposium 2024, 2024
Originally released as GPTFuzzer. Geekcon 2023 Breakthrough Award. Adopted by major LLM providers and integrated into Microsoft Azure PyRIT.
Recommended citation: Jiahao Yu, Xingwei Lin, Zheng Yu, Xinyu Xing. (2024). "LLM-Fuzzer: Scaling Assessment of Large Language Model Jailbreaks." USENIX Security.
Download Paper
Soft-Label Integration for Robust Toxicity Classification
Published in Neural Information Processing Systems (NeurIPS) 2024, 2024
Featured in MIT Technology Review China.
Recommended citation: Zelei Cheng*, Xian Wu*, Jiahao Yu*, Shuo Han, Xin-Qiang Cai, Xinyu Xing. (2024). "Soft-Label Integration for Robust Toxicity Classification." NeurIPS.
Download Paper
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
Published in International Conference on Machine Learning (ICML) 2025, 2025
Recommended citation: Zihao Wang, Yibo Jiang, Jiahao Yu, Heqing Huang. (2025). "The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)." ICML.
Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs’ Ethical Boundaries
Published in USENIX Security Symposium 2025, 2025
USENIX Security 2025 Long Talk.
Recommended citation: Jiahao Yu, Haozheng Luo, Jerry Yao-Chieh Hu, Wenbo Guo, Yan Chen, Han Liu, Xinyu Xing. (2025). "Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs’ Ethical Boundaries." USENIX Security.
Download Paper
PatchAgent: A Practical Program Repair Agent Mimicking Human Expertise
Published in USENIX Security Symposium 2025, 2025
USENIX Security 2025 Long Talk. CSAW 2025 Technical Impact Runner-up. Foundation of the AIxCC Team 42-b3yond-bug solution.
Recommended citation: Zheng Yu, Ziyi Guo, Yuhang Wu, Jiahao Yu, Meng Xu, Dongliang Mu, Yan Chen, Xinyu Xing. (2025). "PatchAgent: A Practical Program Repair Agent Mimicking Human Expertise." USENIX Security.
Download Paper
BlockScan: Detecting Anomalies in Blockchain Transactions
Published in Neural Information Processing Systems (NeurIPS) 2025, 2025
Recommended citation: Jiahao Yu, Xian Wu, Hao Liu, Wenbo Guo, Xinyu Xing. (2025). "BlockScan: Detecting Anomalies in Blockchain Transactions." NeurIPS.
Download Paper
GPO: Learning from Critical Steps to Improve LLM Reasoning
Published in Neural Information Processing Systems (NeurIPS) 2025, 2025
Featured in MIT Technology Review China.
Recommended citation: Jiahao Yu, Zelei Cheng, Xian Wu, Xinyu Xing. (2025). "GPO: Learning from Critical Steps to Improve LLM Reasoning." NeurIPS.
Download Paper
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
Published in International Conference on Machine Learning (ICML) 2026, 2026
Recommended citation: Haozheng Luo, Yimin Wang, Jiahao Yu, Binhui Wang, Yan Chen. (2026). "Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations." ICML.
Decoupled Alignment for Robust Plug-and-Play Adaptation
Published in Conference on Language Modeling (COLM) 2026, 2026
Recommended citation: Haozheng Luo*, Jiahao Yu*, Wenxin Zhang, Jialong Li, Chenghao Qiu, Yimin Wang, Eric Hanchen Jiang, Jerry Yao-Chieh Hu, Yan Chen, Binghui Wang, Xinyu Xing, Han Liu. (2026). "Decoupled Alignment for Robust Plug-and-Play Adaptation." COLM.
Download Paper
Locus: Agentic Predicate Reasoning for Directed Fuzzing
Published in International Conference on Software Engineering (ICSE) 2026, 2026
Recommended citation: Jie Zhu, Chihao Shen, Ziyang Li, Jiahao Yu, Yizheng Chen, Kexin Pei. (2026). "Locus: Agentic Predicate Reasoning for Directed Fuzzing." ICSE.
PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs
Published in IEEE Transactions on Information Forensics and Security (TIFS), 2026
Recommended citation: Jiahao Yu*, Yangguang Shao*, Hanwen Miao, Junzheng Shi. (2026). "PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs." IEEE TIFS.
Download Paper
Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
Published in arXiv preprint arXiv:2509.12434, 2026
1st on SWE-bench Lite and 5th on SWE-bench Verified among open-weight models.
Recommended citation: Jiahao Yu, Zelei Cheng, Xian Wu, Xinyu Xing. (2026). "Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization." arXiv:2509.12434.
Download Paper