Jialiang (Kaelin) Dong ☕️
Jialiang (Kaelin) Dong

PhD Candidate

About Me

Hi, I’m Jialiang (or Kaelin) Dong, a Ph.D. candidate at the University of New South Wales. My research centers on the security of open-source software supply chains and the security of AI systems. Along the way, I’ve had the opportunity to present my work at leading venues such as NDSS, DSN, and TASLP.

Download CV
Interests
  • OSS Supply Chain Security
  • AI System Security
Education
  • PhD - Cyber Security

    University of New South Wales

  • MPhi - Computer Science and Technology

    North China Electric Power University

  • BSc - Computer Science and Technology

    North China Electric Power University

📚 My Research

My research focuses on cybersecurity, with particular emphasis on open-source software supply chain security and AI system security.

In the domain of open-source software, I explore the security of third-party libraries within software ecosystems, analyze potential risks in the vulnerability disclosure process, and study the automated identification and analysis of patches.

In terms of AI system security, my work primarily addresses security issues during the deployment of AI models, while also maintaining a strong interest in the intrinsic weakness of the models themselves. 😃

Featured Publications
Recent Publications
(2025). Ghosts in DBMS: Revealing the Security Impacts of Silent Fixes. The 3rd International Conference on Data Security and Privacy Protection (DSPP).
(2025). From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis. The 28th European Conference on Artificial Intelligence (ECAI).
(2025). What Lies Beneath: An Empirical Study of Silent Vulnerability Fixes in Open-Source Software. The 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).
(2025). Enhancing Security in Third-Party Library Reuse - Comprehensive Detection of 1-day Vulnerability through Code Patch Analysis. ISOC 32th Network and Distributed System Security Symposium (NDSS).
(2024). WEDA: Exploring Copyright Protection for Large Language Model Downstream Alignment. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP).
Recent & Upcoming Talks
Recent News