top of page

Breaking Language Models: A Deep Dive into AI Security Flaws with Nicholas Carlini and Itay Yona

  • Writer: Shanni Gurkevitch
    Shanni Gurkevitch
  • Sep 4
  • 1 min read

Nicholas Carlini and Itay Yona from Google DeepMind on the shift from academic/theoretical attacks to practical attacks on production AI systems and the intersection between traditional security mindsets and machine learning.



 
 
bottom of page