Anshuman Suri

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, and LLM-related vulnerabilities.

news

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	UVA Engineering covered a story on our work on evaluating Membership Inference Attacks on Large Language Models?.
Oct 08, 2024	Presented our work Do Membership Inference Attacks Work on Large Language Models? at COLM in Philadelphia .
Sep 06, 2024	Started as a postdoc at Khoury, Northeastern supervised by Alina Oprea. Hello, Boston !
Jul 26, 2024	Xiao presented our work Do Parameters Reveal More than Loss for Membership Inference at the HiLD workshop at ICML in Vienna .

latest posts

Nov 26, 2024	Reassessing EMNLP 2024’s Best Paper: Does Divergence-Based Calibration for Membership Inference Attacks Hold Up?
Nov 12, 2024	My submission to the ETI Challenge
Nov 08, 2023	My submission to the TDC Trojan Detection Challenge

selected publications

SAGA: A Security Architecture for Governing AI Agentic Systems

Georgios Syros^*, Anshuman Suri^*, Cristina Nita-Rotaru, and 1 more author

arXiv preprint arXiv:2504.21034, 2025

Bib PDF

@article{syros2025saga,
  title = {SAGA: A Security Architecture for Governing AI Agentic Systems},
  author = {Syros, Georgios and Suri, Anshuman and Nita-Rotaru, Cristina and Oprea, Alina},
  journal = {arXiv preprint arXiv:2504.21034},
  year = {2025}
}

Do Parameters Reveal More than Loss for Membership Inference?

Anshuman Suri, Xiao Zhang, and David Evans

Transactions on Machine Learning Research (TMLR), 2024

Bib PDF Code

@article{suri2024do,
  title = {Do Parameters Reveal More than Loss for Membership Inference?},
  author = {Suri, Anshuman and Zhang, Xiao and Evans, David},
  journal = {Transactions on Machine Learning Research (TMLR)},
  year = {2024},
  url = {https://arxiv.org/abs/2406.11544},
}

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

Bib PDF Code Website

@inproceedings{duan2024membership,
  title = {Do Membership Inference Attacks Work on Large Language Models?},
  author = {Duan, Michael and Suri, Anshuman and Mireshghallah, Niloofar and Min, Sewon and Shi, Weijia and Zettlemoyer, Luke and Tsvetkov, Yulia and Choi, Yejin and Evans, David and Hajishirzi, Hannaneh},
  year = {2024},
  booktitle = {Conference on Language Modeling (COLM)},
}

Formalizing and Estimating Distribution Inference Risks

Anshuman Suri, and David Evans

Proceedings on Privacy Enhancing Technologies, 2022

Bib PDF Video Code

@article{suri2022formalizing,
  title = {Formalizing and Estimating Distribution Inference Risks},
  author = {Suri, Anshuman and Evans, David},
  journal = {Proceedings on Privacy Enhancing Technologies},
  year = {2022},
}