JADEPUFFER: The AI Malware With No Human in the loop

About this episode

What if AI stopped being the assistant to cybercriminals and became the attacker itself? That's no longer hypothetical. JADEPUFFER is the first documented case of ransomware run entirely by an AI agent: it broke into a production database, hit a wall mid-attack, then found another way in within 31 seconds, faster than most human penetration testers can react. Rob Maas, Field CTO at ON2IT, sits down with Yuri Wit, SOC DevOps Engineer at ON2IT, to trace how agentic malware evolved out of AI-assisted attacks into a threat that plans, executes, and pivots entirely on its own.

🔗 Episode resources, transcript and show notes: https://threat-talks.com 
📝 Read the companion blog post: 
🎙️ Subscribe on Spotify and Apple Podcasts, links below.

Threat Talks is a podcast by ON2IT cybersecurity and AMS-IX. We delve deep into the dynamic world of cybersecurity, one episode at a time. New episode every Tuesday.

#ThreatTalks #ZeroTrust #firewallsecurity  #NetworkSecurity #CyberSecurity #infosec 

Charpters: 
00:00:00 Cold open: can AI become the attacker?
00:01:42 PromptLock and PromptSteal: proof of concept to real world
00:04:24 The agentic malware trend and the local LLM question
00:07:24 JADEPUFFER: ransomware run entirely by an AI agent
00:09:58 Proof of concept, or a live-fire test?
00:11:30 Intent-driven attacks and shrinking detection windows
00:16:34 Zero Trust: what to do about it starting now

🔔 Follow and Support our channel! 🔔
=== 
► YOUTUBE: https://youtube.com/@ThreatTalks
► SPOTIFY: https://open.spotify.com/show/1SXUyUEndOeKYREvlAeD7E
► APPLE: https://podcasts.apple.com/us/podcast/threat-talks-your-gateway-to-cybersecurity-insights/id1725776520

👕 Receive your Threat Talks T-shirt
https://threat-talks.com/

🗺️ Explore the Hack's Route in Detail 🗺️
https://threat-talks.com

🕵️ Threat Talks is a collaboration between @ON2IT and @AMS-IX