(Last Updated: October 16, 2026)

I am a master’s student in Machine Learning at MBZUAI, where I am advised by Prof. Salem Lahlou, Prof. Nils Lukas, and Prof. Kun Zhang. I am currently a visiting researcher at Carnegie Mellon University, where I work with Prof. Niloofar Mireshghallah.

My research aims to build AI systems that remain trustworthy as they become more capable and autonomous. To achieve this goal, I focus on four fundamental research questions:

(i) Robustness: How can we develop AI systems that perform reliably across diverse and unforeseen conditions?

(ii) Security: How can we identify and mitigate vulnerabilities that adversaries with bounded capabilities can exploit in AI systems?

(iii) Privacy: How can we quantify and limit sensitive information leakage from AI systems?

(iv) Safety: How can we understand and mitigate risks of harm associated with AI systems?

Previously, I worked on explainable cyberbullying detection and multimodal content moderation. I received my bachelor’s degree in Computer Science and Engineering from IIT Patna, where I was fortunate to be advised by Prof. Sriparna Saha and Prof. Pushpak Bhattacharyya. My undergraduate thesis received the Best Bachelor’s Thesis Award at IIT Patna. I was also a research assistant at the Singapore University of Technology and Design, where I worked with Prof. Roy Lee.