Anshuman Suri

Postdoc, Northeastern University

prof_pic.jpg

177 Huntington Ave

Boston, MA

I am a postdoctoral fellow at Northeastern University, supervised by Alina Oprea. I obtained my PhD from University of Virginia, where I was extremely fortunate to be advised by Professor David Evans. My primary area of research is privacy/security in machine learning at a broad level, with fine-grained topics exploring membership inference, user inference, LLMs.

news

Feb 03, 2025 Georgios will be presenting our work on defending against backdoors in FL at New England Systems Day.
Jan 24, 2025 Our blogpost talking about critical flaws in the evaluation of a recent EMNLP best-paper has been accepted to the ICLR blogpost track!
Nov 14, 2024 :newspaper: UVA Engineering covered a story on our work on evaluating Membership Inference Attacks on Large Language Models?.
Oct 08, 2024 :placard: Presented our work Do Membership Inference Attacks Work on Large Language Models? at COLM in Philadelphia :sunny:.
Sep 06, 2024 Started as a postdoc at Khoury, Northeastern supervised by Alina Oprea. Hello, Boston :cityscape:!

latest posts

selected publications

  1. iha.png
    Do Parameters Reveal More than Loss for Membership Inference?
    Anshuman Suri, Xiao Zhang, and David Evans
    Transactions on Machine Learning Research (TMLR), 2024
  2. mia_llm.png
    Do Membership Inference Attacks Work on Large Language Models?
    Michael Duan*Anshuman Suri*, Niloofar Mireshghallah, and 7 more authors
    In Conference on Language Modeling (COLM), 2024
  3. dist_inf.png
    Formalizing and Estimating Distribution Inference Risks
    Anshuman Suri, and David Evans
    Proceedings on Privacy Enhancing Technologies, 2022