I am pursuing my Ph.D. at the National University of Singapore,
advised by Dr. Mohan Gurusamy and
Dr. Dinil Mon Divakaran. I recently interned at A*STAR Institute of Advanced Intelligence and Computing (A*STAR IAIC). I
graduated from BITS Pilani, India with a B.E. in
Electrical and Electronics Engineering. Previously, I worked at Microsoft and Flipkart.
My research focuses on building and evaluating trustworthy AI systems. I aim to understand when, why, and under what
conditions AI systems fail to uphold their intended guarantees. My research interests include:
- Secure & Reliable Autonomous Agents: Evaluating and strengthening the security of autonomous agents that
interact with external tools, with applications in retrieval-augmented generation and
cyber threat intelligence.
- AI Safety & Adversarial Robustness: Examining how adversarial attacks expose vulnerabilities in LLMs and
their safeguards, including failures in safety alignment and retrieval-augmented systems.
- Mechanistic Interpretability & Auditing of LLMs: Investigating the internal representations and
mechanisms
underlying model behavior, and developing methods to audit knowledge editing and machine unlearning.
Feel free to reach out if you'd like to discuss my research or explore potential collaborations.
