Lucas Rosenblatt
PhD Candidate, Center for Responsible AI @NYU.

Hi, I’m Lucas
I am a fifth-year PhD candidate in Computer Science at NYU advised by Julia Stoyanovich and working closely with Christopher Musco (NYU), Bill Howe (UW) and Rachel Cummings (Columbia).
I am a member of the NYU Center for Responsible AI and the Theoretical Computer Science Group @ NYU.
My research develops trustworthy and privacy-preserving algorithms, focusing on differentially private synthetic data, algorithmic fairness, and privacy for large language models (LLMs), among other things. I am supported by an NSF Graduate Research Fellowship.
Research Overview
I try to design and evaluate approaches that are theoretically sound, practically useful, and socially impactful. For example, I’ve worked on…
- Differentially Private Synthetic Data: Algorithms and reproducibility-focused benchmarks for improved deployment of synthetic data in health and policy contexts.
- LLM Privacy & Security: Threat models for auxiliary-knowledge attacks and studying safe DP fine-tuning (as well as, more watermarking.
- Algorithmic Fairness: Re-considering foundational fairness metrics and finding approximate satisfiability conditions for multiple group metrics.
Selected Publications
- Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data. NeurIPS 2025.
- Sharper Bounds for Chebyshev Moment Matching with Applications to Differential Privacy and Beyond. COLT 2025.
- Differential Privacy Under Class Imbalance: Methods and Empirical Insights. ICML 2025.
- Fragments to Facts: Partial-Information Fragment Inference from LLMs. ICML 2025.
- Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy. VLDB 2023 [Best Paper Runner-Up]
See the full list on my google scholar profile.
Industry Research Experience
-
Google Research (NYC), Student Researcher, June 2025 – Present
Working with Ryan Mckenna and Natalia Ponomareva as part of Servei Vassilvitskii’s group, on tabular data privacy problems with open-source Gemma models. -
Microsoft AI Development Acceleration Program (MAIDAP), ML Engineer/Researcher, June 2019 – 2021
AI rotational program serving Microsoft organizations with applied research in machine learning.
Rotations: Grey Systems Lab, Microsoft+Harvard OpenDP (Smartnoise), Microsoft News, Fairlearn.
Teaching
I have taught or TA’d eight courses across graduate and undergraduate levels.
- Full instructor: (Responsible Data Science) (NYU CDS, Spring 2025)
- Section Leader: (Responsible Data Science) On three occasions. (NYU CDS, Spring 2023-Fall 2025)
- Teaching Assistant: (Algorithmic Machine Learning & Data Science) (NYU CS, Fall 2022)
- Teaching Assistant: (Integrated Intro to Computer Science 17 & 18) (Brown University, 2016-2017)
- Teaching Assistant: (User Interfaces & User Experiences) (Brown University, 2018)
Selected Awards & Recognition
- Theory & Practice of Differential Privacy 2025 Keynote
- SIGMOD Research Highlight (Epistemic Parity: Reproducibility as an Evaluation Metric for DP)
- VLDB Best Paper (Runner-Up) (Epistemic Parity: Reproducibility as an Evaluation Metric for DP)
- NSF Graduate Research Fellowship
Service
- Conference Reviewing: ICLR 2026, 2025, AISTATS 2026, 2025, Neurips 2025, 2024, KDD 2025, ICML 2025, FAccT 2025, TPDP 2025, SOSA 2024, CHI 2023
-
Event Organization:
- Lead organizer, NYU Privacy Day (Spring ‘24)
- Co-organizer, NAIRR Community-Informed Policies Workshop (Summer ‘24)
Outside of Research
I converted a school bus into a mobile home and write whenever I can. I also make pots.
News
Sep 19, 2025 | Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data was accepted to NeurIPS 2025! Excited to present this work in San Diego this December along with Shlomi, feel free to reach out if you’re attending and want to chat. |
---|---|
Jun 19, 2025 | Our paper (Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data), exploring what we can do under DP when generating public tabular data with LLMs, was selected for a Spotlight Presentation (top 10% of submissions) at the FMSD Workshop @ICML2025! |
May 19, 2025 |
(Belatedly, and happily) sharing that we have two forthcoming papers at ICML 2025 (say hi in Vancouver!),
|
May 18, 2025 | Very excited to (belatedly) announce that our work, Sharper Bounds for Chebyshev Moment Matching with Applications to Differential Privacy and Beyond, was accepted to COLT 2025. Say hi in Lyon : ) |
Apr 22, 2025 | Some new work (pre-print here!) I’m really happy with that explores what we can under DP when generating public tabular data with LLMs, with Shlomi Hod and Julia Stoyanovich. This of course assumes that LLMs can truly be considered public data, which is up for debate… |
Apr 21, 2025 | I will join Google Research this summer (2025) as a Research Intern working on data privacy problems. |
Nov 8, 2024 | New pre-print with Rachel Cummings and Marco Avella Medina: Differential Privacy Under Class Imbalance: Methods and Empirical Insights. Very happy with how the work turned out, and there’s still tons to be done in this space! We presented a preliminary version of the work at TPDP 2024. |
Oct 2, 2024 | Teal Witter and I just posted our preprint (under submission): FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness. Really excited about some clever evaluation schemes for assessing fairness AND uncertainty under one umbrella benchmark! |
Aug 11, 2024 | New work that I’m very excited about, Sharper Bounds for Chebyshev Moment Matching with Applications to Differential Privacy and Beyond with Chris Musco, Cam Musco, and Apoorv Vikram Singh. Of the applications of some cool theory in this work: Chebyshev moment matching is a promising mechanism for learning private synthetic distributions! We presented an abstract of the work at TPDP 2024, and the full version is under submission. |
Mar 30, 2024 | Our paper Laboratory-Scale AI: Open-Weight Models are Competitive Even in Low-Resource Settings was accepted to FAccT 2024. This work was led by the indomitable Robert Wolfe; much credit to him, and happy to have been part of the team! |
Feb 5, 2024 | Excited to be organizing the Spring iteration of NYC Privacy Day, to be held at NYU on April 19th, 2024. Privacy Day is a seasonal event that unites privacy folks from NYC institutions; hosting rotates between Columbia, NYU, Google and Cornell Tech. RSVP through the website if you can make it! |
Dec 11, 2023 | Two papers forthcoming at AAAI 2024: |