Steve Gibson
Security Now (Audio)
Booby Trapping LLMs - AI Frenzy in Cybercrime
- Published
- October 14, 2026
- Duration
- 2h 49m
- Summary source
- description
- Last updated
- Oct 14, 2026
Discusses llm, anthropic, ai-regulation.
Summary
Hosts: Steve Gibson and Leo Laporte Think your open-source AI model is safe? This episode uncovers how LLMs can be secretly booby-trapped with undetectable backdoors, raising the stakes for anyone deploying AI in serious environments. Anthropic cuts live Internet access during testing. Will LLM technology turn out to be an uncontrollable dead end? What al…
Intelligent Report
Sign in to read teasers, or upgrade to Research Pro to commission intelligent report for this episode. Learn more →
Show notes
Hosts: Steve Gibson and Leo Laporte Think your open-source AI model is safe? This episode uncovers how LLMs can be secretly booby-trapped with undetectable backdoors, raising the stakes for anyone deploying AI in serious environments. Anthropic cuts live Internet access during testing. Will LLM technology turn out to be an uncontrollable dead end? What alternative AI technologies are underway? Anthropic offers free AI vulnerability scanning for open source. South Korean banks hit by Claude-drive
Themes
- llm
- anthropic
- ai-regulation