Safe Mode Podcast cover art

Safe Mode Podcast

By: Safe Mode Podcast
  • Summary

  • Podcast by Safe Mode Podcast
    All rights reserved
    Show More Show Less
Episodes
  • Josh Harguess on AI red-teaming; an Israeli info op targets the U.S.
    Jun 6 2024
    To address AI risks, policymakers and technologists around the world have embraced the concept of AI red-teaming — the adversarial testing of AI models. But AI red-teaming is such a new concept that few people know how to conduct such tests. The discipline of AI red-teaming very much remains under development, but as AI systems are rolled out far and wide, this discipline is only going to become more important to make sure that AI tools work as intended. On this episode of Safe Mode, host Elias Groll sits down with Josh Harguess, the AI security chief at Cranium AI who is one of the few bona fide experts in the field, to dive deep on how to carry out AI red-teaming. CyberScoop reporter Derek Johnson also joins the show to discuss an Israeli information operation targeting audiences in the United States and Canada.
    Show More Show Less
    37 mins
  • Joe Sullivan on his legal battle with the feds; the latest on Russian influence operations
    Jun 3 2024
    Joe Sullivan on his legal battle with the feds; the latest on Russian influence operations by Safe Mode Podcast
    Show More Show Less
    47 mins
  • Omkhar Arasaratnam on open source security; AI dogfighting
    May 23 2024
    In recent weeks, a series of troubling operations targeting open source software libraries have been uncovered in which bad actors — likely tied to nation states — have attempted to use social engineering to be designated as maintainers of security critical libraries. Operations such as these have the potential to insert backdoors in widely used software libraries that provide the building blocks of modern computing. As the general manager of the Open Source Software Security Foundation, Omkhar Arasaratnam is on the frontlines of protecting the open source software ecosystem, and on this episode of Safe Mode, he sits down with host Elias Groll to discuss what’s needed to improve the security of some of the world’s most widely used software. DefenseScoop reporter Mikayla Easley also joins the show to discuss her reporting about how the Air Force is experimenting with putting AI behind the controls of American fighter jets.
    Show More Show Less
    36 mins

What listeners say about Safe Mode Podcast

Average customer ratings

Reviews - Please select the tabs below to change the source of reviews.