I am a 2^nd year Ph.D. student in Computer Science at the University of Illinois Urbana-Champaign, advised by Prof. Gang Wang in the Siebel School of Computing and Data Science. I also collaborate with Prof. Varun Chandrasekaran and Prof. Huan Zhang.

I study security risks in foundation model training and deployment. My research is driven by three core questions:

• What are the threat models that adversaries can exploit in foundation model training and deployment?
• What is the root cause of unsafe failure modes in LLMs?
• How can we train models to ensure these causes don’t occur?

Recently, I co-led the creation of PurpCode, which is the first open-source reasoning model for cybersafety, winning the Amazon Nova AI Challenge (2025).

I completed my undergraduate studies from IIIT-Delhi, where I had the good fortune of working with Prof. Tanmoy Chakraborty (now at IIT Delhi), and Prof. Zubair Shafiq (at UC Davis), and Prof. Ganesh Bagler.

Internship. I am looking for both Industrial and Academic Internships in the areas of Machine Learning, and Security & Privacy. Feel free to reach out!

Collaboration. I am always looking to work with undergrads and MS students! Feel free to send me an email with the title [Together] in the subject line!

Industry experience

Prior Research Experience