What does it take to trick an AI agent? Not a whole lot, it turns out. This week, panelists Nick Bradley, Claire Nuñez and Jeff Crume join host Matt Kosinski to discuss a couple of new methods for hijacking AI agents and breaking their guardrails. We also talk recent evolutions in DDoS attack trends, the legacy of zero trust and some glaring security flaws in an extremely popular AI training app. Plus: We ring in Cybersecurity Awareness Month with the traditional airing of grievances. 00:00 – Introduction 01:38 – Tricking AI agents 15:18 – The DDoS comeback 26:03 – 15 years of zero trust 36:02 – Neon exposes user calls 44:34 – Cybersecurity myths The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity. Subscribe to the IBM Think newsletter: https://www.ibm.com/account/reg/us-en/signup?formid=news-urx-52120 Follow the Security Intelligence podcast on your preferred platform: https://www.ibm.com/think/podcasts/security-intelligence Learn more about cybersecurity: https://www.ibm.com/think/security

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related