Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy arXiv
Spotlight at NeurIPS 2026
Oral Presentation at RE-Data @ COLM 2026; Lightning Talk at TAG-DS 2026
Elena Ghazi
I am a third-year PhD student in Computer Science at Harvard, where I am very fortunate to be advised by Flavio Calmon and Salil Vadhan. My research interests include privacy-preserving AI, AI for health, and their intersection.
I am interning at Boston Children's Hospital's Computational Health Informatics Program (CHIP), working on AI for health with Scott Wang and Michael Lingzhi Li.
I am part of Harvard's Information Theory Lab and Theory of Computation Group, and the OpenDP open-source software project.
Before joining Harvard, I was a software engineer at Google, working on privacy and compliance for wearables and health data.
Check out the recap of the differential privacy for health and genomics workshop that we organized!
OpenDP Blog Differential Privacy for Health and Genomics Workshop Recap Main takeaways from the workshop on differential privacy for health and genomics. August 24, 2026
Selected updates
- Our hypothesis testing under local DP paper received a Spotlight at NeurIPS! It was also selected for an oral presentation at RE-Data @ COLM 2026.
- I'm interning at Boston Children's Hospital, working on AI for health with the Computational Health Informatics Program!
- I received my Master of Science in Computer Science from Harvard!
- Co-organized the Differential Privacy for Health and Genomics workshop. Check out the recap!
- The Differential Privacy Deployments Registry was featured by Harvard SEAS News!
- The registry paper was accepted to the IEEE Symposium on Security and Privacy!
- The deployment registry project won Best Poster/Demo at NYC Privacy Day!
Selected papers
Making Privacy Public: Toward a Differential Privacy Deployment Registry arXiv
2026 IEEE Symposium on Security and Privacy
Best Poster/Demo at NYC Privacy Day 2025
Featured
Harvard SEAS News Privacy Goes Public With New Database News story on the Differential Privacy Deployments Registry and the Harvard research behind it. March 30, 2026 OpenDP Blog Launching the Differential Privacy Deployments Registry Project announcement covering the registry launch, NIST proposal, and user-study research. November 25, 2025
