Protecting Patients: Privacy-Preserving Computing in Patient Data

Protecting Patients: Privacy-Preserving Computing in Patient Data

From UC San Diego (Video) by UCTV

May 12, 2026 · 35 min

About this episode

Farinaz Koushanfar discusses how privacy-preserving computation can enable the use of sensitive health data while protecting patient privacy.

Privacy-preserving computation can help hospitals and researchers use sensitive health data without exposing it. Farinaz Koushanfar, Ph.D., UC San Diego, explains how secure computation and distributed learning make it possible to collaborate on medical data while protecting patient privacy. Koushanfar examines secure multi-party computation, zero-knowledge proofs, and federated and split learning, helping clarify how health systems can work together despite data silos, incompatibility, security threats, and re-identification risk. This work helps explain how medical AI can learn from private data more safely and points toward more secure, robust, and trustworthy healthcare systems. Series: "Exploring Ethics" [Health and Medicine] [Humanities] [Science] [Show ID: 41367]

People in this episode

Guest: Farinaz Koushanfar

Topics covered

  • privacy-preserving computation
  • health data
  • secure computation
  • medical AI
  • patient privacy
  • collaboration
  • healthcare systems

Keywords

  • privacy
  • health data
  • secure computation
  • federated learning
  • medical AI
  • patient privacy
  • data silos
  • security threats

Mentioned in this episode

Organizations: UC San Diego, UCTV

More episodes of UC San Diego (Video)

Explore listener stats, chart rankings, contacts and more on the UC San Diego (Video) podcast page.