๐Ÿฆฅ About Me

Hi, I am Jiahao Liu (ๅˆ˜ๅฎถ่ฑช). Currently, I am a Ph.D. candidate (advised by Prof. Zhenkai Liang) in CURIOSITY Research Group at National University of Singapore (NUS). I received my B.E. degree in Computer Science at Chu Kochen Honors College of Zhejiang University (ZJU). Apart from Computer Science, I am also interested in Economic and Finance, earning a minor degree in Finance.

My research interests lie primarily in AI for security, with a focus on designing and adapting emerging machine learning techniques (e.g., graph neural networks and large language models) to address real-world security challenges such as malware analysis, program analysis, and vulnerability assessment. More recently, I have been working on AI security, with particular emphasis on agent security. My research investigates inherent threats in agent-based systems, including risks of data leakage between the agent's core reasoning module (โ€œbrainโ€) and external tools, as well as inconsistencies across different agent layers, ranging from design principles to action planning and execution sequences.

๐Ÿ“ Publications

* co-first authors

[Security 2025] Fuzzing the PHP Interpreter via Dataflow Fusion

Yuancheng Jiang, Chuqi Zhang, Bonan Ruan, Jiahao Liu, Roland Yap, Zhenkai Liang, Manuel Rigger

34th Usenix Security Symposium

Distinguished Paper Award

Paper | Code | Slides

[ASE 2025] A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis

Zhiwei Lin, Bonan Ruan, Jiahao Liu, Weibo Zhao

40th IEEE/ACM International Conference on Automated Software Engineering, Tool Demonstrations

Paper| Code | Slides

[EMNLP 2025] PsyScam: A Benchmark for Psychological Techniques in Real-World Scams

Shang Ma, Tianyi Ma, Jiahao Liu, Wei Song, Zhenkai Liang, Xusheng Xiao, Yanfang Ye

30th Empirical Methods in Natural Language Processing, Findings

Paper | Code | Slides

[NDSS 2025] UI-CTX: Understanding UI Behaviors with Code Contexts for Mobile Applications

Jiawei Li*, Jiahao Liu*, Jian Mao, Jun Zeng, Zhenkai Liang

32nd Network and Distributed System Security Symposium

Paper | Code | Slides

[NDSS 2025] ProvGuard: Detecting SDN Control Policy Manipulation via Contextual Semantics of Provenance Graphs

Ziwen Liu, Jian Mao, Jun Zeng, Jiawei Li, Qixiao Lin, Jiahao Liu, Jianwei Zhuge, Zhenkai Liang

32nd Network and Distributed System Security Symposium

Paper | Code | Slides

[ASE 2024] VulZoo: A Comprehensive Vulnerability Intelligence Dataset

Bonan Ruan, Jiahao Liu, Weibo Zhao, Zhenkai Liang

39th IEEE/ACM International Conference on Automated Software Engineering, Tool Demonstrations

Paper | Code | Slides

[ASE 2024] MaskDroid: Robust Android Malware Detection with Masked Graph Representations

Jingnan Zheng*, Jiahao Liu*, An Zhang, Jun Zeng, Ziqi Yang, Zhenkai Liang, and Tat-Seng Chua

39th IEEE/ACM International Conference on Automated Software Engineering

Paper | Code | Slides

[RAID 2024] KernJC: Automated Vulnerable Environment Generation for Linux Kernel Vulnerabilities

Bonan Ruan, Jiahao Liu, Chuqi Zhang, Zhenkai Liang

27th International Symposium on Research in Attacks, Intrusions and Defenses

Best Practical Paper Award

Also present at Black Hat Asia 2025

Paper | Code | Slides

[ICSE 2024] Detecting Logic Bugs in Graph Database Management Systems via Injective and Surjective Graph Pattern Transformation

Yuancheng Jiang, Jiahao Liu, Jinsheng Ba, Roland YAP Hock Chuan, Zhenkai Liang, Manuel Rigger

46th IEEE/ACM International Conference on Software Engineering

Paper | Code | Slides

[ICSE 2023] Learning Graph-based Code Representations for Source-level Functional Similarity Detection

Jiahao Liu*, Jun Zeng*, Xiang Wang, Zhenkai Liang

45th IEEE/ACM International Conference on Software Engineering

Paper | Code | Slides

[S&P 2022] ShadeWatcher: Recommendation-guided Cyber Threat Analysis using System Audit Records

Jun Zeng, Xiang Wang, Jiahao Liu, Yinfang Chen, Zhenkai Liang, Tat-Seng Chua, Zheng Leong Chua

43rd IEEE Symposium on Security and Privacy

Paper | Code | Slides

[ISSTA 2022] TeLL: Log Level Suggestions via Modeling Multi-level Code Block Information

Jiahao Liu, Jun Zeng, Xiang Wang, Kaihang Ji, Zhenkai Liang

31st ACM International Symposium on Software Testing and Analysis

Paper | Code | Slides

๐Ÿ’ฌ Talks

[04/2025] Automated Vulnerable Environment Generation for Linux Kernel Vulnerabilities, Singapore

[02/2025] UI-CTX: Understanding UI Behaviors with Code Contexts for Mobile Applications, San Diego

[10/2024] MaskDroid: Robust Android Malware Detection with Masked Graph Representations, Sacramento

[05/2023] Learning Graph-based Code Representations for Source-level Functional Similarity Detection, Melbourne

[07/2022] TeLL: Log Level Suggestions via Modeling Multi-level Code Block Information, Virtually

๐Ÿ“– Education

[08/2020 ~ present] Ph.D. Candidate in Computer Science, National University of Singapore

[09/2016 ~ 06/2020] Major in Computer Science & Minor in Finance, Zhejiang University

๐Ÿ… Awards

[08/2025] Distinguished Paper Award, USENIX Security 2025

[10/2024] Best Practical Paper Award, RAID 2024

[01/2023] Research Achievement Award

[08/2020] NUS Research Scholarship

[09/2019] Second-Class Scholarship for Outstanding Merits

[09/2018] Shu Ping Prize Scholarship

[09/2017] National Encouragement Scholarship

[09/2017] Second-Class Scholarship for Outstanding Merits

๐Ÿ“š Teaching Assistant

[12/2023 ~ 05/2024] Web Security (TIC4304)

[06/2022 ~ 12/2023] Computer Security (CS3235)

[12/2020 ~ 05/2021] Web Security (CS5331)

[07/2020 ~ 12/2020] Computer Security Practice (CS4238)