Vinith Suriyakumar
MIT EECS, LIDS, IMES
I am a fourth year PhD student at MIT EECS where I am advised by Dr. Ashia Wilson and Dr. Marzyeh Ghassemi. I also collaborate frequently with Dr. Dylan Hadfield-Menell. My research focuses on uncovering and addressing privacy, security, and safety risks in machine learning. Currently, my efforts are focused on foundation models (e.g. LLMs, diffusion models, and multimodal models). Examples of specific topics include: unlearning, backdoors, adversarial attacks, differential privacy, and copyright. Feel free to reach out if you are interested in chatting about or collaborating on any of these areas!
Previously in my PhD, I worked on algorithmic fairness, the role of race in medicine, health inequities in maternal health, and applications to organ procurement processes. I completed my Masters in May 2021 at the University of Toronto & Vector Institute advised by Dr. Marzyeh Ghassemi, Dr. Nicolas Papernot, Dr. Berk Ustun, and Dr. Anna Goldenberg. My thesis was focused on differential privacy and algorithmic fairness in machine learning for healthcare.
UROP & M.Eng Advising: My next availability for advising UROPs and M.Eng students is Fall 2025. I advise students interested in working on questions in my direct research areas as described above. I typically advise one student per academic year.

news
Jun 3, 2024 | Our work on developing a philosophical framework to better reason about the impact of algorithmic decision-making on equal opportunity, Algorithmic Pluralism: A Structural Approach Towards Equal Opportunity, was awarded Best Paper at FAccT 2024! |
---|---|
Jan 15, 2024 | Our work on formalizing and analyzing how to fairly use group attributes in prediction models, One-Shot Empirical Privacy Estimation for Federated Learning, was awarded an Oral presentation at ICLR 2024! |
Apr 29, 2023 | Our work on formalizing and analyzing how to fairly use group attributes in prediction models, When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction, was awarded an Oral presentation at ICML 2023! |
May 14, 2022 | I’m excited to announce that our work from my Summer 2021 internship at Google on Public Data-Assisted Mirror Descent for Private Model Training was accepted to ICML 2022! |
Mar 30, 2022 | I’m excited to announce that I’ve accepted an offer to return to Google this summer as a Student Researcher working with Dr. Peter Kairouz and Dr. Galen Andrew! |