What do I look like?

  • ...

Links

Who am I?

I am a computer scientist working on differential privacy (DP). I design and analyze DP algorithms in settings where there is no "trusted curator." My thesis work was on the shuffle model and I continue to explore how to use crytographic primitives for DP. I strive to minimize sample efficiency, communication complexity, and vulnerability to attacks.

My current affiliation is Google NY, where I am a research scientist. Prior to that, I was a postdoctoral fellow in the Department of Computer Science at Georgetown University, where I was fortunate to work with Prof. Kobbi Nissim and Chao Yan.

I earned my PhD. at Northeastern University's Khoury College of Computer Science. My advisor was Prof. Jonathan Ullman.

Earlier, I attended Stuyvesant High School and earned my BS at New York University's Tandon School of Engineering.

Recent News

  • 13 May '24: I officially begin my full-time position at Google!
  • 7 May '24: I am a co-author of a TPDP'24 submission.
  • 16 April '24: I am a co-author of a Google whitepaper on Confidential Federated Computations.

Publications, Extended Abstracts, and Pre-prints

  • Differentially Private Distributed Mean Estimation with Malicious Security.
    With Laasya Bangalore and Muthuramakrishnan Venkitasubramaniam.
    Presented at the ninth Theory and Practice of Differential Privacy workshop (TPDP 2023)
  • Necessary Conditions in Multi-server Differential Privacy [arXiv].
    With Chao Yan.
    Presented at the 14th Innovations in Theoretical Computer Science conference (ITCS 2023).
  • Differentially Private Histograms in the Shuffle Model from Fake Users [IEEE, arXiv].
    With Maxim Zhilyaev.
    Presented at the 43rd IEEE Symposium on Security and Privacy (S&P 2022).
  • Pure Differential Privacy from Secure Intermediaries [arXiv].
    With Chao Yan.
  • Shuffle Private Stochastic Convex Optimization [OpenReview, arXiv].
    With Matthew Joseph, Jieming Mao, and Binghui Peng.
    Presented at the 10th International Conference on Learning Representations (ICLR 2022).
  • The Limits of Pan Privacy and Shuffle Privacy for Learning and Estimation [arXiv,ACM].
    With Jonathan Ullman.
    Presented at the 53rd ACM Symposium on Theory of Computing (STOC 2021).
  • Connecting Robust Shuffle Privacy and Pan-Privacy [arXiv, SIAM].
    With Victor Balcer, Matthew Joseph, Jieming Mao.
    Presented at ACM-SIAM Symposium on Discrete Algorithms (SODA 2021).
  • Separating Local and Shuffled Differential Privacy via Histograms [DROPS, arXiv].
    With Victor Balcer.
    Presented at the Conference on Information-Theoretic Cryptography (ITC 2020).
  • Private Query Release Assisted by Public Data [arXiv].
    With Raef Bassily, Shay Moran, Aleksandar Nikolov, Jonathan Ullman, Zhiwei Steven Wu.
    Presented at the International Conference on Machine Learning (ICML 2020)
  • Manipulation Attacks in Local Differential Privacy [arXiv, JPC].
    With Adam Smith and Jonathan Ullman.
    Presented at S&P 2021
  • Distributed Differential Privacy via Shuffling [SpringerLink, arXiv].
    With Adam Smith, Jonathan Ullman, David Zeber, and Maxim Zhilyaev.
    Presented at the IACR International Conference on Theory and Application of Cryptographic Techniques (EUROCRYPT 2019).
  • Skyline Identification in Multi-Armed Bandits [IEEE, arXiv].
    With Ravi Sundaram and Jonathan Ullman.
    Presented at the International Symposium on Information Theory (ISIT 2018).

Contact

My email address is [firstname].[lastname] -at- gmail -dot- com