Hao Wang (王皓)
FIT 4-206 Tsinghua University, Beijing, China 100084
[email protected]
Institute for Network Science and Cyberspace
CTFer of Redbud and Tea Deliverers
Education
- 2020 - Current: Ph.D. candidate in Institute for Network Sciences and Cyberspace, Tsinghua University
- 2016 - 2020: B.E. in Information Security, University of Science and Technology of Chinese (USTC)
Research Interests
- Large Language Models
- AI for Security
- Binary Code Analysis
- Fuzzing
Project Experience
Machine Language Model [Official Website] [Report] (July 2023 - Present)
Lead Researcher of machine language model project in collaboration with VUL337 and 01.AI
Convolutional Code Search with Layer-wise Attention (July 2019 - June 2020)
Research Intern at Microsoft Research Asia, Machine Learning Group, Stars of Tomorrow Internship
Mentors: [Jiang Bian], [Jia Zhang]
Awards and Honors
- 2024 1st place in Matrix Cup Cybersecurity Competition – Artificial Intelligence (Large Model) Challenge
- 2023 3rd place in NIPS 2023 TDC Red-Teaming Competition, Large Model Subtrack
- 2023 2nd place in “China Cyber Wushu Cup” National Cybersecurity Elite Competition
- 2023 2nd place in DEF CON CTF Final 2023
- 2023 1st place in DEF CON CTF Qualifier 2023
- 2022 3rd prize of Network Security Track PKS System Special Competition in the Final DCIC
- 2022 2nd prize of Network Security Track in the Final DCIC
- 2022 2nd place in Peek Geek CTF Final
- 2022 1st place in Peek Geek CTF Qualifier
- 2022 1st place in AutoDriving CTF @ DEFCON 30
- 2021 2nd place in XiangYunCup 2021
- 2021 2nd place in L3HCTF 2021
- 2021 3rd place in DEF CON CTF 29 Final
- 2021 4th place in AutoDriving CTF 2021 @ DEFCON 29
- 2021 4th place in AntCTF 2021
- 2021 2nd place in *CTF 2021
- 2020 1st place in ByteCTF 2020 Final
- 2020 1st place in ByteCTF 2020 Online
- 2020 1st place in WCTF Campus 2020
Publications
ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models [paper]
Jingwei Yi, Junhao Yin, Ju Xu, Peng Bao, Yongliang Wang, Wei Fan, Hao Wang. ArXiv 2025
An Engorgio Prompt Makes Large Language Model Babble On [paper]
Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang, Tianwei Zhang, Hao Wang, Hewu Li, Qi Li, Chao Zhang, Ke Xu, Han Qiu.
In the International Conference on Learning Representations (ICLR’25)
SmartTrans: Advanced Similarity Analysis for Detecting Vulnerabilities in Ethereum Smart Contracts [paper]
Longfei Chen, Hao Wang, Yuchen Zhou, Taiyu Wong, Jialai Wang, Chao Zhang.
In the IEEE Transactions on Dependable and Secure Computing (TDSC’25)
OpTrans: Enhancing Binary Code Similarity Detection with Function Inlining Re-Optimization [paper]
Zihan Sha, Yang Lan, Chao Zhang, Hao Wang, Zeyu Gao, Bolun Zhang, Hui Shu.
To appear in the Empirical Software Engineering (ESE’25)
PromeTrans: Bootstrap Binary Functionality Classification with Knowledge Transferred from Pre-trained Models [paper]
Zihan Sha, Chao Zhang, Hao Wang, Zeyu Gao, Bolun Zhang, Yang Lan, Hui Shu.
To appear in the Empirical Software Engineering (ESE’25)
BinQuery: A Novel Framework for Natural Language-Based Binary Code Retrieval [paper]
Bolun Zhang, Zeyu Gao, Hao Wang, Yuxin Cui, Siliang Qin, Chao Zhang, Kai Chen, Beibei Zhao.
To appear in _the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA’25)
Virtual Compiler Is All You Need For Assembly Code Search [paper]
Zeyu Gao, Hao Wang, Yuanda Wang, Chao Zhang.
In _the Annual Meeting of the Association for Computational Linguistics (ACL’24)
Llasm: Naming Functions in Binaries by Fusing Encoder-only and Decoder-only LLMs [paper]
Zihan Sha, Hao Wang, Zeyu Gao, Hui Shu, Bolun Zhang, Ziqing Wang, Chao Zhang.
In the ACM Transactions on Software Engineering and Methodology (TOSEM’24)
Improving ML-based Binary Function Similarity Detection by Assessing and Deprioritizing Control Flow Graph Features [paper]
Jialai Wang, Chao Zhang, Longfei Chen, Yi Rong, Yuxiao Wu, Hao Wang, Wende Tan, Qi Li, Zongpeng Li.
In the USENIX Security Symposium (USENIX Security’24)
CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision [paper] [code] [model]
Hao Wang, Zeyu Gao, Chao Zhang, Zihan Sha, Mingyang Sun, Yuchen Zhou, Wenyu Zhu, Wenju Sun, Han Qiu, Xi Xiao.\
In the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA’24)
CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection [paper] [code]
Hao Wang, Zeyu Gao, Chao Zhang, Mingyang Sun, Yuchen Zhou, Han Qiu, Xi Xiao.
In the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA’24)
How Far Have We Gone in Vulnerability Detection Using Large Language Models [paper] [code] [media report(Chinese)]
Zeyu Gao, Hao Wang, Yuchen Zhou, Wenyu Zhu, Chao Zhang. ArXiv 2023
kTrans: Knowledge-Aware Transformer for Binary Code Embedding [paper]
Wenyu Zhu, Hao Wang, Yuchen Zhou, Jiaming Wang, Zihan Sha, Zeyu Gao, Chao Zhang. ArXiv 2023
jTrans: Jump-Aware Transformer for Binary Code Similarity Detection [paper] [code] [media report(Chinese)]
Hao Wang, Wenjie Qu, Gilad Katz, Wenyu Zhu, Zeyu Gao, Han Qiu, Jianwei Zhuge, Chao Zhang
In the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA’22), Daejeon, South Korea, July 2022
COSEA: Convolutional code search with layer-wise attention [paper]
Hao Wang, Jia Zhang, Yingce Xia, Jiang Bian, Chao Zhang, Tie-Yan Liu. ArXiv 2020