701: Generative A.I. without the Privacy Risks (with Prof. Raluca Ada Popa)
Super Data Science: ML & AI Podcast with Jon Krohn
Importance of Discretion in Confidential Computing for Privacy Protection
The chapter delves into the significance of discretion in confidential computing systems to maintain privacy, by setting policies for sharing encrypted data and revealing outcomes under specific conditions. It discusses examples like collaboratively training aggregate models while controlling data reveal to catch money launderers and testing datasets in ad tech. Additionally, the chapter explores the importance of confidential computing in generative AI, emphasizing protecting user privacy by placing models in cloud enclaves to process encrypted queries.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
