Zhejiang University · Ph.D. in Computer Science and Technology
State Key Laboratory of Blockchain and Data Security · Advisor: Prof. Kui Ren (Fellow of AAAS, ACM, CCF, and IEEE)
My research focuses on intrinsic security of LLM agents, model watermarking and intellectual property protection, backdoor defense, and trustworthy AI systems.
State Key Laboratory of Blockchain and Data Security · Advisor: Prof. Kui Ren (Fellow of AAAS, ACM, CCF, and IEEE)
Ranked 4th of 46 · Innovation and Entrepreneurship Management Program, Chu Kochen Honors College
In 2024, I co-founded Hangzhou Zhulong Zhiyuan Technology Co., Ltd., where I built an enterprise-grade agent R&D and delivery team from the ground up and continue to explore pathways from research to real-world products.
Related research outcomes have been widely covered by dozens of leading media outlets in China and abroad, including China Education News Network, Zhejiang Satellite TV, Hunan Satellite TV, Yahoo Finance, the Associated Press, and Caitong News.
Research interests:
LLM Agent Security, Trustworthy AI, Model IP Protection, and AI Systems.
Highlights:
10 papers published or accepted at international conferences including KDD, WWW,
IEEE S&P, and ICLR; invited reviewer for NeurIPS, ACL, and ICML; 11 invention
patents granted or published as a principal inventor.
National Natural Science Foundation of China · Young Student Research Program
Focusing on intrinsic security risks in LLM agents, this project develops a three-layer active defense framework spanning the full perception–reasoning–action pipeline.
SRTP National Innovation Project
This project developed domain-embedding-based model watermarking that reprograms a target model into an owner-controlled latent space. It preserves harmlessness while remaining robust against a range of model-removal attacks, and received the Best Creative Project award at the National College Student Innovation Annual Conference—one of only 12 projects nationwide.
KDD · Dataset & Benchmark Track · First Author
A holistic benchmark for evaluating LLM capabilities across nine Web3 subdomains, combining objective knowledge assessment with open-ended reasoning tasks. It introduces a contamination-aware evaluation pipeline and analyzes the accuracy, reasoning reliability, and cost efficiency of 31 leading models.
WWW · Demo Track · Co-first Author
An LLM-driven multi-agent simulation framework that jointly models transient affective responses and persistent cognitive beliefs in public-opinion propagation. Evaluations on 15 real-world crises show that it reconstructs opinion trajectories more faithfully than existing simulation baselines.
ICASSP · First Author
A physics-inspired Transformer for complex-valued signals that explicitly incorporates relative phase and wave interference into self-attention. The architecture preserves amplitude–phase consistency and demonstrates strong performance on PolSAR classification and wireless-channel prediction.
Complex-valued signal processing with phase-interference self-attention.
Python · 103 starsMulti-agent simulation of cognitive-affective public opinion dynamics.
TypeScript / Python · WWW ’26A benchmark dataset and framework for evaluating Web3 LLMs.
Hugging Face · KDD ’26PromptDefender, a platform for protecting the IP of system prompts.
Zhulong Technology ranked first in its group and joined the innovation showcase.
Led the development of a robust backdoor defense system.
Led the development of NetDP, a differential-privacy data processing system.
The model-watermarking project was selected among 12 national winners.
Recognized for academic excellence, research innovation, and student leadership.
Received the college’s highest student honor and nine university-level exemplary distinctions.