Topic
Lex Fridman
Michael Kearns introduces differential privacy as a robust technical framework designed to offer genuine hope for individual privacy in an era where data aggregation can easily identify specific users. Unlike weaker anonymization methods, this approach establishes a rigorous definition by comparing …
Lex Fridman
Andrew Trask, a researcher and author of *Grokking Deep Learning*, presents privacy-preserving AI (PPAI) technologies designed to solve the critical problem of data scarcity in machine learning. Currently, researchers often cannot answer vital questions regarding sensitive health issues like dementi …
Lex Fridman
In this episode of the Lex Fridman Podcast, Dawn Song, a computer science professor at UC Berkeley and expert in security and machine learning, addresses the fundamental inevitability of vulnerabilities in software systems. She explains that while formal verification techniques can prove certain pro …