Rishav Chourasia

School of Computing,

NUS, Singapore 117417.

I am a Ph.D. student at NUS School of Computing and a research scientist at Betterdata. I am interested in differential privacy, especially private optimization, privacy auditing and machine unlearning.

Before starting my Ph.D., I got my Bachelor’s degree in Computer Science and Engineering from the IIT Guwahati.

news

Dec 30, 2024	I’ll be giving a talk on Laplace Transform Interpretation of Differential Privacy at the PPAI workshop.
Dec 23, 2024	My paper on Laplace Transform Interpretation of Differential Privacy was accepted at FORC 2025.
Nov 19, 2024	I submitted my Ph.D. thesis “Learning and Unlearning with Noisy Gradient Descent” for evaluation!
Oct 8, 2024	Betterdata won the US Department of Homeland Security’s S&T Awards Contract to develop privacy enhancing synthetic data generation capabilities.
Aug 26, 2024	I successfully cleared my thesis proposal with wonderful reviews!
Jul 18, 2023	I joined Betterdata as a part-time student researcher. I’ll be working on privacy auditing for Tabular synthetic data generators.
May 18, 2023	I’ll be giving a talk on my ICML 2023 paper Forget Unlearning: Towards True Data Deletion in Machine Learning at FORC 2023 at Stanford University.
Feb 15, 2023	Added a blog post on Flaws in Machine Unlearning!
May 10, 2022	I’ll be interning at Google Brain this summer, collaborating with Krishnamurthy Dvijotham and Abhradeep Thakurta in the Privacy and Security research team.
Sep 28, 2021	My paper on Differential Privacy Dynamics of Langevin Diffusionand Noisy Gradient Descent got accepted as spotlight at NeurIPS, 2021 (among 3% of submissions).
Jan 22, 2021	Updated my blog on Differential Privacy in ML!

selected publications

FORC 2025
& PPAI 2025
(oral)

Laplace Transform Interpretation of Differential Privacy

Rishav Chourasia, Uzair Javaid, and Biplap Sikdar

In Proceedings of the 6th annual Symposium on Foundations of Responsible Computing, 2025

arXiv Bib

@article{chourasia2024laplace,
  bibtex_show = {true},
  abbr = {FORC 2025},
  abbr2 = {& PPAI 2025},
  abbr3 = {(oral)},
  selected = {true},
  title = {Laplace Transform Interpretation of Differential Privacy},
  author = {Chourasia, Rishav and Javaid, Uzair and Sikdar, Biplap},
  journal = {In Proceedings of the 6th annual Symposium on Foundations of Responsible Computing},
  arxiv = {2411.09142},
  year = {2025}
}

ICML 2023
& FORC 2023

Forget Unlearning: Towards True Data-Deletion in Machine Learning

Rishav Chourasia, and Neil Shah

In Proceedings of the 40th International Conference on Machine Learning, 2023

Bib PDF

@inproceedings{pmlr-v163-chourasia23forget,
  bibtex_show = {true},
  abbr = {ICML 2023},
  abbr2 = {& FORC 2023},
  selected = {true},
  title = {Forget Unlearning: Towards True Data-Deletion in Machine Learning},
  author = {Chourasia, Rishav and Shah, Neil},
  booktitle = {Proceedings of the 40th International Conference on Machine Learning},
  year = {2023},
  volume = {163},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  pdf = {chourasia2023forget.pdf}
}

NeurIPS 2021
(spotlight)

Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent

Rishav Chourasia, Jiayuan Ye, and Reza Shokri

In Advances in Neural Information Processing Systems, 2021

Bib PDF

@inproceedings{NIPS2021_7c6c1a7b,
  bibtex_show = {true},
  author = {Chourasia, Rishav and Ye, Jiayuan and Shokri, Reza},
  abbr = {NeurIPS 2021},
  abbr2 = {(spotlight)},
  selected = {true},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Ranzato, M. and Beygelzimer, A. and Liang, P.S. and Vaughan, J.W. and Dauphin, Y.},
  pages = {},
  publisher = {Curran Associates, Inc.},
  title = {Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent},
  url = {https://proceedings.neurips.cc/paper/2021/file/7c6c1a7bfde175bed616b39247ccace1-Paper.pdf},
  volume = {34},
  year = {2021},
  pdf = {NIPS2021_7c6c1a7b.pdf}
}