Mobile AI System Security
Characterizing deployed AI system security, such as adversarial vulnerabilities, model tampering, and model protection.
I’m an incoming Assistant Professor at School of Computer Science and Information Technology, Adelaide University, starting in November 2026. I obtained my PhD from The University of Melbourne, where I was fortunate to be advised by A/Prof. Xingliang Yuan and Prof. Chunyang Chen.
My research interests lie in Trustworthy On-device AI Systems, specifically focusing on three directions:
Post-Deployment Model Safety
Assessing model safety after deployment, such as guardrail bypasses and training-free backdoor attacks.
Embodied AI System Security
Exploring security challenges in embodied AI systems, such as robustness, resilience, and secure interaction.
My research has been incorporated into influential AI safety research and policy materials from Meta’s Llama 2, Google DeepMind’s STAR, Monetary Authority of Singapore’s Emerging Risks and Opportunities of Generative AI for Banks, Center for Democracy & Technology’s Comments to NTIA on Open Foundation Models, and Council of the European Union’s ChatGPT in the Public Sector – overhyped or overlooked?.
I am looking for self-motivated PhD students to join my group, and interested applicants are encouraged to email me at jinxwasstorm@gmail.com with your CV. I also welcome research assistants, master students, and undergraduate students who are interested in working with me on ongoing research projects.