Department of Computer Science and Engineering
The Hong Kong University of Science and Technology
Email: daoyuan [at] cse.ust.hk
; dywu [at] ie.cuhk.edu.hk
Gmail: daoyuan0x
DBLP |
Google Scholar
I am currently a Research Assistant Professor (PhD Supervisor, with responsibilities including grant applications and teaching) at HKUST CSE. Prior to joining HKUST, I was a Senior Research Fellow at Nanyang Technological University (NTU) for one year and a Senior Researcher at HKRC for six months. Before that, I spent three wonderful years as an independent Research Assistant Professor in the Department of Information Engineering at The Chinese University of Hong Kong (CUHK). I also served as an Adjunct Assistant Professor at CUHK IE for one year, from 2022 to 2023. Before joining CUHK, I earned Ph.D. in 2019 from Singapore Management University (SMU) in the School of Computing and Information Systems. My PhD study was generously supported by the Secure Mobile Center (SMC) PhD Scholarship (as the sole awardee; plus the GRE requirement was waived). Before pursuing my PhD, I received M.Phil. from Department of Computing at Hong Kong Polytechnic University in 2015 and B.E. from Department of Information Security at Nanjing University of Posts and Telecommunications in 2011.
My research focuses on three areas: (i) Large Language Model and AI Security, (ii) Blockchain and Web3 Security, and (iii) Mobile and Software Security. Over the years, I have made the following representative works:
RAG4Sec: the first to exploit the concept of RAG or its variant for cybersecurity tasks, including LLM4Vuln [arXiv'24] for vulnerability detection (via GPT-summarized knowledge), PropertyGPT [NDSS'25] for formal verification (via example-based ICL), ACFix [arXiv'24] for vulnerability repair (via mined common practice), and more.
GPTScan: the first [ICSE'24] to deeply connect LLM with static analysis, opening door to sound LLM-based code analysis.
SelfDefend: the first generic LLM jailbreak defense framework that allows LLMs to defend themselves in a practical manner.
Tune4Sec: customized tuning for cybersecurity tasks, including iAudit [ICSE'25] by combining fine-tuning and LLM agents, LLMImitation [ICSE'24] for code model imitation, PTM4AWI [arXiv'24] for Actionable Warning Identification (AWI), and more.
BlockScope: a search-based patch vs. code similarity analysis tool [NDSS'23] for discovering 100+ vulnerabilities in top blockchains, including Dogecoin (new CVE-2021-37491), Binance's BSC Chain (a bug bounty), and Optimism/Base/Mantle.
AC4Web3: the first to study access control bugs in OpenZeppelin [USENIX'24] and customized function modifiers [ISSTA'23].
BackDroid: a very creative search-based CG technique, on-the-fly bytecode search, to address a fundamental limitation in Android app analysis. It enables usage in Open Ports [NDSS'19], MtdScout [EuroS&P'24], and DSDK [EMSE'21, WASA'17].
MopEye: the first non-intrusive crowdsourcing app MopEye [ATC'17] for security and networking research, leading to further work on AcuteMon [CoNEXT'16], UpDroid [WiSec'18], Dataset [IWQoS'19], NetMon [NDSS'19], and SideNet [TII'21].
A pioneering contribution to Android Component security (60+ CVEs) and WebView security (e.g., CVE-2014-7224 for Android and CVE-2015-5921 for iOS) with an ITF grant, Local [ISC'14] and Remote Attacks [MoST'15], and IABI Usability [RAID'21].
I am looking for highly self-motivated students/RAs with expertise in AI/LLM;Blockchain/Mobile;PL/Fuzzing to join VPRLab.
Strong candidates are also welcome to contact my close collaborators: Prof. Yang Liu, Prof. Shuai Wang, Prof. Debin Gao,
Prof. Yingjiu Li, Prof. Robert Deng, Prof. Lingxiao Jiang, Prof. David Lo, and Prof. Kehuan Zhang. I can help recommend.
Large Language Model and AI Security: LLMs for Cybersecurity; Security of LLMs; AI Safety.
ForSec:
PropertyGPT [NDSS'25],
GPTScan [ICSE'24],
iAudit [ICSE'25],
ML4AWI [CSUR'24],
SideNet [TII'21],
UpDroid [WiSec'18],
LLM4Vuln [arXiv'24],
ACFix [arXiv'24],
and
PTM4AWI [arXiv'24].
AISec/Quality:
HEDiff [ICSE'25],
Portia [EMNLP'24Main],
LLMImitation [ICSE'24],
SelfDefend [arXiv'24],
DataScope [arXiv'24],
PDoctor [arXiv'24],
MLM4VDL [arXiv'24],
and
VRPTEST [arXiv'23].
Blockchain and Web3 Security: analyzing Blockchain, Smart Contract, and Layer-2/Rollup security.
Web3 matters not for replacing the Internet, but for enabling trustless value transfer, which the centralized Internet cannot offer.
ZepScope [USENIX'24],
BlockScope [NDSS'23],
SoMo [ISSTA'23],
and MineBlockVuln [FSE'22].
LLM-related are listed above.
Mobile and Software Security: static/dynamic/vulnerability/malware/privacy analysis; Rust/EdgeAI security.
BackDroid [DSN'21; very creative tech, taking years of R&D],
Insecure Open Ports [NDSS'19],
MtdScout [EuroS&P'24],
DSDK Inconsistency [EMSE'21, WASA'17],
Insecure PendingIntents [Blackhat Europe'21],
IABI Usability Insecurity [RAID'21],
VoIP Fuzzing [DIMVA'20],
MineAndroVuln [AsiaCCS'19],
SCLib [CODASPY'18],
Remote Webview Attacks [MoST'15],
Local Webview File:// Attack [ISC'14],
LiCA [RAID'22],
App Repackaging [TDSC'21],
Native Stack [ICISC'15],
and
ECVDetector [arXiv'14].
My recent focus in this area includes Rust/EdgeAI security and usability privacy studies, the latter in collaboration with my wife.
I am also interested in network and web measurement, blockchain-based decentralized apps, and AI-based smart systems.
MopEye [ATC'17], MopEye Dataset [IWQoS'19], Speedtest Inaccuracy [INFOCOM'15, TMC'17], and AcuteMon [CoNEXT'16].
AGChain [DLT'24] and iExam [arXiv'22].
P33 |
AGChain: A Blockchain-based Gateway for Trustworthy App Delegation from Mobile App Markets DLT '24 |
P32 |
PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation NDSS '25 |
P31 |
Testing and Understanding Deviation Behaviors in FHE-hardened Machine Learning Models ICSE '25 |
P30 |
Combining Fine-tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications ICSE '25 |
P29 |
Split and Merge: Aligning Position Biases in LLM-based Evaluators EMNLP '24 Main |
P28 |
Machine Learning for Actionable Warning Identification: A Comprehensive Survey CSUR '24 |
P27 |
Using My Functions Should Follow My Checks: Understanding and Detecting Insecure OpenZeppelin Code in Smart Contracts USENIX Security '24 |
P26 |
MtdScout: Complementing the Identification of Insecure Methods in Android Apps via Source-to-Bytecode Signature Generation and Tree-based Layered Search EuroS&P '24 |
P25 |
GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis ICSE '24 |
P24 |
On Extracting Specialized Code Abilities from Large Language Models: A Feasibility Study ICSE '24 |
P23 |
Beyond “Protected” and “Private”: An Empirical Security Analysis of Custom Function Modifiers in Smart Contracts ISSTA '23 |
P22 |
BlockScope: Detecting and Investigating Propagated Vulnerabilities in Forked Blockchain Projects NDSS '23 |
P21 |
An Empirical Study of Blockchain System Vulnerabilities: Modules, Types, and Patterns FSE '22 |
P20 |
LiCA: A Fine-grained and Path-sensitive Linux Capability Analysis Framework RAID '22 |
P19 |
On the Usability (In)Security of In-App Browsing Interfaces in Mobile Apps RAID '21 |
P18 |
When Program Analysis Meets Bytecode Search: Targeted and Efficient Inter-procedural Analysis of Modern Android Apps in BackDroid DSN '21 |
P17 |
Active Warden Attack: On the (In)Effectiveness of Android App Repackage-Proofing TDSC '21 |
P16 |
Deep-Learning-Based App Sensitive Behavior Surveillance for Android Powered Cyber-Physical Systems TII '21 |
P15 |
Scalable Online Vetting of Android Apps for Measuring Declared SDK Versions and Their Consistency with API Calls EMSE '21 |
P14 |
Understanding Android VoIP Security: A System-level Vulnerability Assessment DIMVA '20 |
P13 |
Towards Understanding Android System Vulnerabilities: Techniques and Insights AsiaCCS '19 |
P12 |
An Empirical Study of Mobile Network Behavior and Application Performance in the Wild IWQoS '19 |
P11 |
Understanding Open Ports in Android Applications: Discovery, Diagnosis, and Security Assessment NDSS '19 |
P10 |
Towards Dynamically Monitoring Android Applications on Non-rooted Devices in the Wild WiSec '18 |
P9 |
SCLib: A Practical and Lightweight Defense against Component Hijacking in Android Applications CODASPY '18 |
P8 |
MopEye: Opportunistic Monitoring of Per-app Mobile Network Performance USENIX ATC '17 |
P7 |
Toward Accurate Network Delay Measurement on Android Phones TMC '17 |
P6 |
Measuring the Declared SDK Versions and Their Consistency with API Calls in Android Apps WASA '17 |
P5 |
Demystifying and Puncturing the Inflated Delay in Smartphone-based WiFi Network Measurement CoNEXT '16 |
P4 |
Stack Layout Randomization with Minimal Rewriting of Android Binaries ICISC '15 |
P3 |
On the Accuracy of Smartphone-based Mobile Network Measurement INFOCOM '15 |
P2 |
Indirect File Leaks in Mobile Applications MoST '15 |
P1 |
Analyzing Android Browser Apps for file:// Vulnerabilities ISC '14 |
R12 |
API-guided Dataset Synthesis to Finetune Large Code Models arXiv '24 |
R11 |
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner arXiv '24 |
R10 |
Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs arXiv '24 |
R9 |
Benchmarking Multi-Modal LLMs for Testing Visual Deep Learning Systems Through the Lens of Image Mutation arXiv '24 |
R8 |
ACFix: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts arXiv '24 |
R7 |
Pre-trained Model-based Actionable Warning Identification: A Feasibility Study arXiv '24 |
R6 |
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper arXiv '24 |
R5 |
LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning arXiv '24 |
R4 |
VRPTEST: Evaluating Visual Referring Prompting in Large Multimodal Models arXiv '23 |
R3 |
iExam: A Novel Online Exam Monitoring and Analysis System Based on Face Detection and Recognition arXiv '22 |
R2 |
MopEye: Monitoring Per-app Network Performance with Zero Measurement Traffic CoNEXT '15 Poster |
R1 |
A Sink-driven Approach to Detecting Exposed Component Vulnerabilities in Android Apps arXiv '14 |
T8 |
Discovering and Investigating Propagated Vulnerabilities from Ethereum to Its Layer-2 Blockchains HITBSecConf '24 |
T7 |
构建基于大模型的智能漏洞审计引擎 AICon HK 2024 |
T6 |
Proof-of-Work vs. Proof-of-Stake: Insights into Fairness and Governance Sustainability from the Blockchain World Business Sustainability Conference '23 |
T5 |
Re-route Your Intent for Privilege Escalation: A Universal Way to Exploit Android PendingIntents in High-profile and System Apps Blackhat Europe '21 |
T4 |
Leveraging Automatic Face Recognition for Online Exam Monitoring and Analysis CUHK Expo '21 |
T3 |
Boosting Android Security through App-, Network-, and System-level Vulnerability Analysis NJUPT Keynote '19 |
T2 |
Cross-Platform Analysis of Indirect File Leaks in Android and iOS Applications HitCon Pacific '17 |
T1 |
On the Feasibility of Automatically Generating Android Component Hijacking Exploits HitCon '14 |
2025 Spring - COMP4541 Blockchain, Cryptocurrencies and Smart Contracts: to teach at HKUST in February 2025.
2022 Fall - IEMS5710 Cryptography, Information Security and Privacy: homepage (only in CUHK) and mirror website (public).
2021 Fall - IERG4130 Introduction to Cyber Security: homepage (only in CUHK) and mirror website (public).
Received the Best Teaching Award of the MScIE Programme 2020-2021.
2021 Spring - IEMS5722 Mobile Network Programming and Distributed Server Architecture: homepage and mirror website.
2020 Fall - IEMS5710 Cryptography, Information Security and Privacy: homepage (only in CUHK) and mirror website (public).
2019 Fall - IEMS5710 Cryptography, Information Security and Privacy: homepage (only in CUHK) and mirror website (public).
PhD Students:
Officially advised: Dr. Xiao Yi (2019 - 2023 at CUHK; First job: researcher at Huawei Hong Kong Research Centre).
Unofficially co-advised: Dr. Han Liu (Apr 2023 - Jun 2024 at NTU; First job: postdoc at HKUST).
Unofficially co-advising: Zicheng Zhang (at SMU since Apr 2020, with gap years), Yuqiang Sun (at NTU since Mar 2023), and a group of PhD students at HKUST Cybersecurity Labs.
Research Assistants:
Juantao Zhong (at Shenzhen Research Institute since Aug/Sep 2024), Yufan Chen (at SMU since Oct 2023, with gap months; co-advised with Prof. Debin Gao, Prof. Yingjiu Li, and Prof. Shuai Wang), Ziyu Lin (at SMU since June 2024, co-advised with Prof. Ximeng Liu and Prof. Robert Deng), and Kaiwen Yang (at HKUST since Jul 2024, co-advised with Prof. Shuai Wang).
Senior Security Expert: Yue Xue (Apr 2023 - Apr 2024 at MetaTrust Labs, still co-advising with Prof. Yang Liu; Next: OKX).
Yuzhou Fang (2021 - 2022 at CUHK; Next: PhD student at USC), Mengjie Chen (2020 - 2021 at CUHK; Next: Mask Network).
Undergraduate Students:
Zimo Ji (at HKUST since May 2024, co-advised with Prof. Shuai Wang).
Yufan Chen (2021 - 2022 at Xidian; Next: SMU), Xu Yang (2021 - 2022 at CUHK; Next: ASTRI).
Four FYP students at CUHK and One at HKUST currently.
MSc Students (at CUHK):
2019 - 2020: Mengjie Chen (DLT'24; Next: CUHK), Lixiang Li (RAID'21; Next: miHoYo), Ming Fang (helped EuroS&P'24; Next: Alibaba), Weiyan Xiong (helped FSE'22; Next: SAP China).
2020 - 2021: Yan Wu (EuroS&P'24; Next: Morgan Stanley China), Siqin Li (explored FPS security).
2021 - 2022: Lu Zhang (helped MagicCrypto; Next: OKX Hong Kong).
Conference Program Committee:
CCS 2025 (Blockchain track), USENIX Security 2025, NDSS 2025, ISSTA 2025, ICSE 2025, CCS 2024 (Software track), ACSAC 2024, RAID 2024, AsiaCCS 2024, ICICS 2024, RAID 2023, ICICS 2023, ICICS 2021, and NOMS 2018.
Conference Shepherd:
NDSS 2025 (for this paper), CCS 2024 (for this paper), RAID 2023 (for this paper), and ICICS 2021 (for this paper).
Workshop Program Committee:
SVM 2025 (co-located with ICSE 2025) and AISTA 2024 (co-located with ISSRE 2024).
Journal Reviewer:
ACM Transactions on Privacy and Security, ACM Transactions on Software Engineering and Methodology, IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Mobile Computing, Journal of Systems and Software, Journal of Information Security and Applications, IEEE Systems Journal, Cybersecurity, and etc.
My calendar of security conferences: academia and industry. Recently used: CCF Conference Deadlines.
I am maintaining a list of interesting computer security papers and a list of mobile app related software engineering papers.
Security Journals: TIFS (special issues), TDSC (special issues), Computers & Security (special issues), TISSEC and JCS.
Storytelling 101: Writing Tips for Academics (by Nick Feamster)
Computer Security Conference Ranking and Statistic (by Guofei Gu)
Top Crypto and Security Conferences Ranking (by Jianying Zhou)
Top Publication Venues in Computer Science (by Andrew Myers)
ArnetMiner CS Rank: conference rank and organization rank.
CCF Conference and Journal Rankings: Security, Networking, System, and Software Engineering.
Google Scholar Metrics in Computer Security, Computing Systems, Computer Networks, and Software Systems.
Industry Cybersecurity Conference Directory, SKKU seclab | Upcoming Events, and Cipher Call-for-papers.