CARVIEW

MOTORHOMES

Select Language

HTTP/2 301 content-type: text/html; charset=utf-8 location: /cloudsecurity/podcast/ep68-how-we-attack-ai-learn-more-at-our-rsa-panel/ x-cloud-trace-context: 7eaa5c151444eb22762d50d51055d913;o=1 date: Sat, 03 Jan 2026 16:11:36 GMT server: Google Frontend content-length: 0 alt-svc: h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 HTTP/2 200 content-type: text/html; charset=utf-8 vary: Accept-Encoding content-security-policy: img-src 'self' https://storage.googleapis.com/cloud-security-podcast/ https://i.ytimg.com/ https://csi.gstatic.com https://www.google.com/images/ https://cloud.google.com/; default-src 'self' 'unsafe-inline' 'unsafe-eval' https://www.youtube.com/ https://apis.google.com/js/gen_204 https://www.google.com/images/; script-src 'unsafe-inline' 'strict-dynamic' http: https: 'sha256-2eNcVUB/y+ah3UbIFL4oUZCIcxvEUi39u+vJJaa/x3Y='; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' https://fonts.gstatic.com; media-src 'self' https://storage.googleapis.com/cloud-security-podcast/ *.libsyn.com https://www.youtube.com/ 'unsafe-inline' 'unsafe-eval'; base-uri 'none'; frame-src 'self' https://feedback-pa.clients6.google.com/ https://www.youtube.com/; object-src 'none' strict-transport-security: max-age=60; includeSubDomains x-content-type-options: nosniff referrer-policy: same-origin cross-origin-opener-policy: same-origin x-frame-options: DENY content-encoding: gzip x-cloud-trace-context: 75f384ad5ef8f154762d50d51055d0ab date: Sat, 03 Jan 2026 16:11:36 GMT server: Google Frontend content-length: 3589 alt-svc: h3=":443"; ma=2592000,h3-29=":443"; ma=2592000 EP68 How We Attack AI? Learn More at Our RSA Panel!

Back

#68

June 6, 2022

EP68 How We Attack AI? Learn More at Our RSA Panel!

Guest:

Nicholas Carlini, Research Scientist @ Google

25:27

Subscribe at Google Podcasts.

Subscribe at Spotify.

Subscribe at Apple Podcasts.

Topics covered:

What is your threat model for a large-scale AI system? How do you approach this problem? How do you rank the attacks?
How do you judge if an attack is something to mitigate? How do you separate realistic from theoretical?
Are there AI threats that were theoretical in 2020, but may become a daily occurrence in 2025?
What are the threat-derived lessons for securing AI?
Do we practice the same or different approaches for secure AI and reliable AI?
How does relative lack of transparency in AI helps (or hurts?) attackers and defenders?

EP68 How We Attack AI? Learn More at Our RSA Panel!

Guest:

Topics covered:

Resources: