Jiaheng Zhang

I am an assistant professor in School of Computing at National University of Singapore (NUS). I am also affiliated with NUS AI Institute and AIDF. I obtained the Ph.D. degree in Computer Science at UC Berkeley, where I was advised by Prof. Dawn Song. I also worked closely with Prof. Yupeng Zhang. And I was a member of RISE Lab, Initiative for Cryptocurrencies & Contracts Lab (IC3), The Berkeley Center for Responsible, Decentralized Intelligence (RDI) and Berkeley AI Research (BAIR).

My research interests lie in LLM/AI security and privacy, applied cryptography, especially zero-knowledge proofs and applications on blockchain and machine learning models. My research of zkBridge focusing on cross-chain bridges in blockchain has been successfully commercialized by Polyhedra Network.

Before coming to Berkeley, I received my Bachelor's degree in ACM Honors Class of Shanghai Jiao Tong University, where I worked under the supervision of Prof. Xiaotie Deng. During my undergraduate, I was also a research intern at Cornell, advised by Prof. Elaine Shi.

I have interned at Meta, NTT Research, Qizhi Institute, and Alibaba. I was supported by the Facebook Fellowship during my PhD. I am listed at Forbes 30 Under 30 Asia and MIT Technology Review Innovators Under 35 Asia Pacific.

I am looking for motivated students to join my group, including visiting PhDs, interns, postdocs, and CSC students. Please send an email to jiahengzhang.recruit AT gmail.com with your CV and transcript.

Email / Google Scholar /

CNN-Verf, A Zero-Knowledge Proof System for Convolutional Neural Network inference with Optimal Complexity
Wenjie Qu*, Yanpei Guo*, Yue Ying, Jiaheng Zhang
Oakland (S&P), 2026

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Yue Liu, Shengfang Zhai, Mingzhe Du, Yulin Chen, Tri Cao, Hongcheng Gao, Cheng Wang, Xinfeng Li, Kun Wang, Junfeng Fang, Jiaheng Zhang, Bryan Hooi
NeurIPS, 2025

Mosformer: Maliciously Secure Three-Party Inference Framework for Large Transformers
Ke Cheng, Yuheng Xia, Anxiao Song, Jiaxuan Fu, Wenjie Qu, Yulong Shen, Jiaheng Zhang
CCS, 2025

NaviDet: Efficient Input-level Backdoor Detection on Text-to-Image Synthesis via Neuron Activation Variation
Shengfang Zhai, Jiajun Li, Yue Liu, Huanran Chen, Zhihua Tian, Wenjie Qu, Qingni Shen, Ruoxi Jia, Yinpeng Dong, Jiaheng Zhang
ICCV (Highlight), 2025

Scalable Collaborative zk-SNARK and Its Application to Fully Distributed Proof Delegation
Xuanming Liu, Zhelei Zhou, Yinghao Wang, Yanxin Pang, Jinye He, Bingsheng Zhang, Xiaohu Yang, Jiaheng Zhang
USENIX Security, 2025

FlipAttack: Jailbreak LLMs via Flipping
Yue Liu, Xiaoxin He, Miao Xiong, Jinlan Fu, Shumin Deng, Yingwei Ma, Jiaheng Zhang, Bryan Hooi
ICML, 2025

Prompt Inversion Attack against Collaborative Inference of Large Language Models
Wenjie Qu, Yuguang Zhou, Yongji Wu, Tingsong Xiao, Binhang Yuan, Yiming Li, Jiaheng Zhang
Oakland (S&P), 2025

HyperPianist: Pianist with Linear-Time Prover and Logarithmic Communication Cost
Chongrong Li, Pengfei Zhu, Yun Li, Cheng Hong, Wenjie Qu, Jiaheng Zhang
Oakland (S&P), 2025

Provably Robust Multi-bit Watermarking for AI-generated Text
Wenjie Qu, Wengrui Zheng, Tianyang Tao, Dong Yin, Yanze Jiang, Zhihua Tian, Wei Zou, Jinyuan Jia, Jiaheng Zhang
USENIX Security, 2025

DeepFold: Efficient Multilinear Polynomial Commitment from Reed-Solomon Code and Its Application to Zero-knowledge Proofs
Yanpei Guo, Xuanming Liu, Kexi Huang, Wenjie Qu, Jiaheng Zhang
USENIX Security, 2025

zkGPT: An Efficient Non-interactive Zero-knowledge Proof Framework for LLM Inference
Wenjie Qu, Yijun Sun, Xuanming Liu, Tao Lu, Yanpei Guo, Kai Chen, Jiaheng Zhang
USENIX Security, 2025

A Fully Pipelined GPU-Accelerated System for Batch Generation of Zero-Knowledge Proofs
Tao Lu, Yuxun Chen, Zonghui Wang, Xiaohang Wang, Wenzhi Chen, Jiaheng Zhang
ASPLOS, 2025

Pianist: Scalable zkRollups via Fully Distributed Zero-Knowledge Proofs [pdf]
Tianyi Liu, Tiancheng Xie, Jiaheng Zhang, Dawn Song, Yupeng Zhang
IEEE Symposium on Security and Privacy (S&P), 2024

Correlation Intractability and SNARGs from Sub-exponential DDH [pdf]
(Alphabetical order) Arka Rai Choudhuri, Sanjam Garg, Abhishek Jain, Zhengzhong Jin, Jiaheng Zhang
Annual International Cryptology Conference (CRYPTO), 2023

zkBridge: Trustless Cross-chain Bridges Made Practical [pdf]
Tiancheng Xie, Jiaheng Zhang, Zerui Cheng, Fan Zhang, Yupeng Zhang, Yongzheng Jia, Dan Boneh, Dawn Song
The ACM Conference on Computer and Communications Security (CCS), 2022

Polynomial Commitment with a One-to-Many Prover and Applications [pdf]
Jiaheng Zhang, Tiancheng Xie, Thang Hoang, Elaine Shi, Yupeng Zhang
USENIX Security Symposium (Security), 2022

Doubly Efficient Interactive Proofs for General Arithmetic Circuits with Linear Prover Time [pdf]
Jiaheng Zhang, Tianyi Liu, Weijie Wang, Yinuo Zhang, Dawn Song, Xiang Xie, Yupeng Zhang
The ACM Conference on Computer and Communications Security (CCS), 2021

Zero Knowledge Proofs for Decision Tree Predictions and Accuracy [pdf] [code]
Jiaheng Zhang, Zhiyong Fang, Yupeng Zhang, Dawn Song
The ACM Conference on Computer and Communications Security (CCS), 2020

Transparent Polynomial Delegation and Its Applications to Zero Knowledge Proof [pdf] [video] [code]
Jiaheng Zhang*, Tiancheng Xie*, Yupeng Zhang, Dawn Song
IEEE Symposium on Security and Privacy (S&P), 2020

Libra: Succinct Zero-Knowledge Proofs with Optimal Prover Computation [pdf] [video] [code]
Tiancheng Xie*, Jiaheng Zhang*, Yupeng Zhang, Charalampos Papamanthou, Dawn Song
Annual International Cryptology Conference (CRYPTO), 2019