Lucas Rosenblatt

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.

---