Jiaheng Zhang

Assistant Professor, computer science, National University of Singapore

Joined

February 2024

Names

Jiaheng Zhang (Preferred)

Emails

****@nus.edu.sg (Confirmed)

Personal Links

Homepage

DBLP

ORCID

Career & Education History

Assistant Professor

computer science, National University of Singapore (nus.edu.sg)

2023 – Present

PhD student

computer science, University of California, Berkeley (berkeley.edu)

2018 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Dawn Song

2018 – 2023

Expertise

Machine Learning Security

Present

privacy preserving machine learning

Present

applied cryptography

Present

Agent safety

Present

Publications

SafeClawBench: An Operating-System Perspective on Evaluating the Security of Claw-like Agent Systems
Peizhi Niu, Shangding Gu, Wenjie Qu, Tianneng Shi, Yuankai Li, Ahmad Tawaha, Hend Alzahrani, Vincent Siu, Boyi Li, Chenguang Wang, Jiaheng Zhang, Basel Alomair, Ming Jin, Muhao Chen, Chi Wang, Costas Spanos, Dawn Song
- ICML 2026 AIWILD
- Readers: Everyone
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu, Mubashara Akhtar, Jiaheng Zhang, Elliott Ash, Markus Leippold, Timothy Baldwin, See-Kiong Ng, Artem Shelmanov, Mrinmaya Sachan
- ICLR 2026 AIWILD
- Readers: Everyone
Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
Tianyi Wu, Mingzhe Du, Yue Liu, Chengran Yang, Terry Yue Zhuo, Jiaheng Zhang, See-Kiong Ng
- ICLR 2026 AIWILD
- Readers: Everyone
Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu, Mubashara Akhtar, Jiaheng Zhang, Elliott Ash, Markus Leippold, Timothy Baldwin, See-Kiong Ng, Artem Shelmanov, Mrinmaya Sachan
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
Tianyi Wu, Mingzhe Du, Yue Liu, Chengran Yang, Terry Yue Zhuo, Jiaheng Zhang, See-Kiong Ng
- ICLR 2026 Trustworthy AI
- Readers: Everyone
GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, and Video
Zhenhao Zhu, Yue Liu, Yanpei Guo, Wenjie Qu, Cancan Chen, Yufei He, Yibo Li, Yulin Chen, Tianyi Wu, Huiying Xu, Xinzhong Zhu, Jiaheng Zhang
- ICLR 2026 Trustworthy AI
- Readers: Everyone
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Zherui Li, Zheng Nie, Zhenhong Zhou, Yufei Guo, Yue Liu, Yitong Zhang, Yu Cheng, Qingsong Wen, Kun Wang, Jiaheng Zhang
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads
Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu, Mubashara Akhtar, Jiaheng Zhang, Elliott Ash, Markus Leippold, Timothy Baldwin, See-Kiong Ng, Artem Shelmanov, Mrinmaya Sachan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems
Yuhao Wang, Wenjie Qu, Shengfang Zhai, Yanze Jiang, Liu Zichen, Yue Liu, Yinpeng Dong, Jiaheng Zhang
- ICLR 2026 Poster
- Readers: Everyone
TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization Models
Yang Dai, Oubo Ma, Xingxing Liang, Longfei Zhang, Xiaochun Cao, Shouling Ji, Jiaheng Zhang, Jincai Huang, Li Shen
- ICLR 2026 Poster
- Readers: Everyone

View all 24 publications

Co-Authors

View all 143 co-authors