Profiles

I study whether AI systems actually work when it matters. A model that performs well on a benchmark is not the same as one that holds up in the real world. That gap is what my research is about.

My work touches three areas:

(1) I analyze how cyberbullying spreads across platforms, because detection models need to reflect how harmful behavior actually moves through social networks.

(2) I build benchmarks to test whether large language models can reason over formal specifications, because that question deserves evidence, not assumption.

(3) I examine how federated learning systems fail under adversarial conditions, because distributed AI carries real security risks that are easy to overlook.

The thread connecting all of this is evaluation. I want to build tools that show us where AI breaks down before real consequences follow. That is the problem I keep returning to, and the one I plan to build my career around.

I conduct this research under the supervision of Dr. Yasin N. Silva and Dr. Mohammed Abuhamad at 🟩Facebook账号 | 越南 真实账号 | UID1000 | 2008-2023年 | 好友15-30 | 微软邮箱 | 无2FA.

Degrees

BS Computer Science (Completed)

MS Data Science (Completed)

PhD Computer Science (In Progress)

Research Interests

AI evaluation and benchmarking, cyberbullying detection, cross-platform contagion analysis, large language model reasoning, formal verification, federated learning security, adversarial robustness, and social computing.

Selected Publications

Google Scholar