Recipient of a NeurIPS outstanding paper award; 2019-20 J.P. Morgan PhD Fellow; Published multiple papers on differentially private learning, synthetic data generation, robust federated learning, etc.; First student paper from his IITM group accepted to NeurIPS 2025; Released a monograph on correlated noise mechanisms for differentially private learning; Received the Google India Research Award; Paper on user inference attacks for LLMs accepted for an oral presentation at EMNLP 2024.
Research Experience
Currently an Assistant Professor and Narayanan Family Foundation Fellow at the Wadhwani School of Data Science & AI and a principal investigator at the Centre for Responsible AI (CeRAI) at IIT Madras; Previously a visiting researcher (postdoc) at Google Research in the Federated Learning team.
Education
PhD: Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Zaid Harchaoui and Sham Kakade; Master's: Carnegie Mellon University, worked with Nina Balcan; Undergraduate: IIT Bombay.
Background
Research interests include privacy-preserving and robust machine learning/AI, particularly the learning and inference of LLMs and generative AI, with applications to healthcare and public good.
Miscellany
Contact: [my-first-name][my-last-initial] @ dsai [dot] iitm [dot] ac [dot] in; Interested in joining? See here.