About

I am a third-year PhD student in Computer Science at Arizona State University, co-advised by Prof. Chitta Baral and Prof. Ruoyu Wang. I expect to complete my PhD in Spring 2028.

Previously, I received my M.S. in AI Engineering (Information Security) from Carnegie Mellon University in 2024, and my B.A. in Computer Science and Economics from Boston College in 2022.

Research Interests

My general research interests lie in Natural Language Processing and its applications in security and software engineering. My recent work focuses on:

• LLM Post-Training – improving model capabilities and safety through supervised fine-tuning and reinforcement learning
• AI Security – securing LLMs and agentic systems against jailbreaks, prompt injection, and adversarial threats
• Multi-Agent Systems – building and evaluating collaborative agentic workflows
• AI for Software Security – applying AI methods to software security and vulnerability analysis

News

• August 2026: We submitted one first-authored paper to NDSS 2027.
• August 2026: My first-authored paper Build-Bench was accepted at TMLR.
• August 2026: My co-first-authored paper CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents was accepted to the EMNLP 2026 Main Conference.
• May–August 2026: I completed a summer internship at Samsung Research America as a Research Intern.
• November 2025: My first-authored paper Build-Bench was accepted at the NeurIPS 2025 Deep Learning for Code workshop.
• November 2025: A paper I co-authored on jailbreaking LLMs via novel complex ciphers was accepted at the NeurIPS 2025 Reliable ML from Unreliable Data workshop.
• September 2024: My first-authored paper Masked Pretraining Strategy for Neural Potentials was published in AIP Advances.