About me

I’m an assistant professor and the 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. My group studies the theory and practice of ML & AI, focusing on privacy-preserving and robust learning of LLMs and generative AI, with applications to healthcare and public good.

Previously, I was a visiting researcher (postdoc) at Google Research in the Federated Learning team. I obtained my PhD from the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where I was fortunate to be advised by Zaid Harchaoui and Sham Kakade. Before that, I worked with Nina Balcan for my Master’s at Carnegie Mellon University and received an undergraduate degree from IIT Bombay.

My research has been recognized by a NeurIPS outstanding paper award and I was a 2019-20 J.P. Morgan PhD Fellow.

Contact me at [my-first-name][my-last-initial] @ dsai [dot] iitm [dot] ac [dot] in.

Research highlights

Some highlights from my previous research include:

• differentially private learning, including optimization [monograph, ICLR ‘24, FOCS ‘24, SaTML ‘25], LLM-based synthetic data generation [NeurIPS ‘25], auditing [NeurIPS ‘23], datasets [NeurIPS ‘23], and LLM privacy attacks [EMNLP ‘24 Oral]
• evaluating synthetic data generation by LLMs and generative AI [NeurIPS ‘21 Outstanding Paper Award, JMLR 2023 Best Papers Track]: Project Page
• robust federated learning, including robust aggregation [FL-ICML ‘20 Long Oral, TSP ‘22 Top 25 Downloaded Article], personalization [ICML ‘22], distributionally robust and differentially private federated learning [DistShift-NeurIPS ‘22 Spotlight, MLJ ‘23, AISTATS ‘23, ICLR ‘24 Spotlight]. The AISTATS paper received the ASA Student Paper Award Honorable Mention. See the project Page

News

• [October 2025] Excited to announce that the first student paper from my IITM group has been accepted to NeurIPS 2025! Congrats to Vishnu, who shows how to use LLMs to generate synthetic text at scale with differential privacy guarantees, using 10x less computational cost than prior work. Joint work with Abhradeep Thakurta.
• [June 2025] Thrilled to announce the release of our monograph on correlated noise mechanisms for differentially private learning! This tutorial is a deep dive into a fascinating area with several exciting open questions. Co-authored with Jalaj Upadhyay and other amazing collaborators from academia and industry. Comments are welcome!
• [June 2025] I’m honoured to be selected as the Narayanan Family Foundation Fellow! A faculty fellowship at IIT Madras is roughly equivalent to an endowed chair position for assistant professors.
• [December 2024] I’m grateful to receive the Google India Research Award!
• [November 2024] Paper on user inference attacks for LLMs accepted for an oral presentation at EMNLP 2024!
• [October 2024] Invited talk at 1st International Conference on Responsible AI for Healthcare (webpage) and at the National AI in Healthcare symposium (webpage)!
• [July 2024] Paper on efficient and near-optimal correlated noise mechanisms for streaming DP has been accepted to FOCS 2024 and an oral presentation at TPDP 2024!
• [June 2024] Gave an invited IEEE Webinar on robust federated learning (Slides Recording)!
• [May 2024] Attended ICLR to present papers on differentially private learning with correlated noise and bias-free distributionally robust learning (Spotlight).
• [May 2024] I joined IIT Madras as an assistant professor! Here are the slides I used for my job talk. I am happy to make other job application material upon request.
• [Mar. 2024] Paper on robust federated learning has been identified as one of IEEE Signal Processing Society’s top 25 downloaded articles from Sept. 2022 - Sept. 2023!
• [Feb. 2024] Concluded my time as a visiting researcher (postdoc) at Google Research where I worked on various aspects of differential privacy at the user-level [final slides, Papers: ICLR ‘24, NeurIPS ‘23, NeurIPS D&B ‘23, ArXiv ‘23]. I’m grateful to the team for such a wonderful experience!
• [Dec. 2023] Paper on MAUVE Scores for Generative AI accepted to JMLR (Best Papers Track)! See the Project Page.
• [Jan. 2023] Paper on Differentially Private Superquantile Aggregation for Federated Learning accepted to the Machine Learning Journal! See the Project Page.
• [Jun. 2022] I defended my PhD! My dissertation and the defense slides are available online.