projects
VUL337-AI for CyberGym

Published: September 19, 2026

VUL337-AI: Reproducing 98.74% of 1,507 Real-World Vulnerabilities on CyberGym with a Single-Model Agent

publications
Sysyphuzz: the Pressure of More Coverage

NDSS 2026 , download

Zezhong Ren , Han Zheng , Zhiyao Feng , Qinying Wang , Marcel Busch , Yuqing Zhang , Chao Zhang , Mathias Payer .

A kernel fuzzer designed to boost exploration of under-tested code regions.

publications
FirmAgent: Leveraging Fuzzing to Assist LLM Agents with IoT Firmware Vulnerability Discovery

NDSS 2026 , download

Jiangan Ji , Chao Zhang , Shuitao Gan , Lin Jian , Hangtian Liu , Tieming Liu , Lei Zheng , Zhipeng Jia .

Leveraging fuzzing to assist LLM agents with IoT firmware vulnerability discovery.

publications
Improving LLM-based Log Parsing by Learning from Errors in Reasoning Traces

ASE 2025 , download

Jialai Wang , Juncheng Lu , Jie Yang , Junjie Wang , Zeyu Gao , Chao Zhang , Zhenkai Liang , Ee-Chien Chang .

Improving LLM-based log parsing by learning from errors in reasoning traces.

publications
Tady: A Neural Disassembler without Structural Constraint Violations

USENIX Security 2025 , download

Siliang Qin , Fengrui Yang , Hao Wang , Bolun Zhang , Zeyu Gao , Chao Zhang , Kai Chen .

A neural disassembler without structural constraint violations based on post-dominance relations.

publications
IDFUZZ: Intelligent Directed Grey-box Fuzzings

USENIX Security 2025 , download

Yiyang Chen , Chao Zhang , Long Wang , Wenyu Zhu , Changhua Luo , Nuoqi Gui , Zheyu Ma , Xingjian Zhang , Bingkai Su .

An intelligent directed grey-box fuzzing solution with neural network guided input mutation.

publications
DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios

ACL 2025 , download

Zeyu Gao , Yuxin Cui , Hao Wang , Siliang Qin , Yuanda Wang , Zhang Bolun , Chao Zhang .

A comprehensive benchmark for evaluating decompiler effectiveness in real-world reverse engineering scenarios.

publications
Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems

ICML 2025 , download

Yutong Wu , Jie Zhang , Yiming Li , Chao Zhang , Qing Guo , Han Qiu , Nils Lukas , Tianwei Zhang .

A defense approach to enhance robustness of multi-agent systems against adversarial attacks.

publications
xFUZZ: A Flexible Framework for Fine-Grained, Runtime-Adaptive Fuzzing Strategy Composition

ISSTA 2025 , download

Dongsong Yu , Yiyi Wang , Chao Zhang , Yang Lan , Zhiyuan Jiang , Shuitao Gan , Zheyu Ma , Wende Tan .

A flexible framework for fine-grained, runtime-adaptive fuzzing strategy composition.

publications
Enhancing Smart Contract Security Analysis with Execution Property Graphs

ISSTA 2025 , download

Kaihua Qin , Zhe Ye , Zhun Wang , Weilin Li , Liyi Zhou , Chao Zhang , Dawn Song , Arthur Gervais .

Clue framework achieves superior smart contract security analysis with high true positive rates and low false positive rates using Execution Property Graphs.

publications
BinQuery: A Novel Framework for Retrieving Binary Function with Natural Language Query

ISSTA 2025 , download

Bolun Zhang , Zeyu Gao , Hao Wang , Yuxin Cui , Siliang Qin , Chao Zhang , Kai Chen , Beibei Zhao .

A novel framework for retrieving binary functions using natural language queries.

publications
DCDiff: Enhancing JPEG Compression via Diffusion-based DC Coefficients Estimation

DAC 2025 , download

Ziyuan Zhang , Han Qiu , Tianwei Zhang , Bin Chen , Chao Zhang .

Enhancing JPEG compression via diffusion-based DC coefficients estimation method.

publications
Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation

CVPR 2025 , download

Jialai Wang , Yuxiao Wu , Weiye Xu , Yating Huang , Chao Zhang , Zongpeng Li , Mingwei Xu , Zhenkai Liang .

Targeted bit-flip attacks on vision transformers via scale factor manipulation.

publications
A Benchmark for Semantic Sensitive Information in LLM’s Outputs

ICLR 2025 , download

Qingjie Zhang , Han Qiu , Di Wang , Yiming Li , Tianwei Zhang , Wenyu Zhu , Haiqing Weng , Liu Yan , Chao Zhang .

A benchmark for semantic sensitive information in LLM’s outputs.

publications
An Engorgio Prompt Makes Large Language Model Babble On

ICLR 2025 , download

Jianshuo Dong , Ziyuan Zhang , Qingjie Zhang , Tianwei Zhang , Hao Wang , Hewu Li , Qi Li , Chao Zhang , Ke Xu , Han Qiu .

An engorgio prompt makes large language model babble on.