Podcast: How to scam an AI agent, DDoS attack trends and busting cybersecurity myths

10/13/20251 min read

black and white robot toy on red wooden table
black and white robot toy on red wooden table

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.

All this and more, on Security Intelligence.

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.

📹 YouTube https://ibm.biz/Bdbd2x
🎧 Casted https://ibm.biz/BdbBv3
🎧 Apple Podcasts https://ibm.biz/BdbdZA
🎧 Spotify https://ibm.biz/BdbdZL

Connect

Let's create stories that connect and inspire. Find me on LinkedIn and follow my store on TikTok.

© 2025. All rights reserved.