whoami?
I am a first (going to second) year Computer Science Ph.D. student at the University of Maryland, College Park, advised by Prof. Yizheng Chen.
My research interests include AI Security, Machine Learning, and Natural Language Processing.
I was a Master of Science in Intelligent Information Systems student at the Language Technologies Institute, CMU, advised by Prof. Maarten Sap, and for a short while, Prof. Aditi Raghunathan, and Prof. Carolyn Rose & Prof. Michael Hilton.
Before that, I was a Research Fellow at Microsoft Research India, working with Prof. Monojit Choudhury, who is now at MBZUAI.
Full list of advisors here.
I have worked on two kinds of problems: AI Ethics, involving moral and cultural biases, and AI Safety, including LLM Jailbreaks, and LLM4Code Security.
news
- August 2025: We, team Purpl3Pwn3rs, were finalists at the Amazon Nova AI Challenge: Trusted AI Track.
- April 2025: Our work NormAd was used by TASC, Google.
- April 2025: Accepted my offer for a Ph.D. at University of Maryland, College Park.
- January 2025: Stayed back at LTI, CMU as a member of staff.
- January 2025: Akhila's and my paper accepted at NAACL
2025:
- June 2024: Joined Bell-Labs as a Research Intern.
- April 2024: Our work from Microsoft accepted at LREC-CoLING 2024:
- October 2023: Our work from Microsoft accepted at EMNLP Findings 2023:
- August 2023: Joined Carnegie Mellon University as a Master's student in
LTI.
- August 2022: Joined Microsoft as a Research Fellow.
- January 2022: Joined Microsoft Research as a Research Intern.
- August 2021: Joined SpeechLab, Nanyang Technological
University as a Research Intern.
- June 2021: Joined Oracle Corporation as an SDE Intern.
