SN 1100: Booby Trapping LLMs - AI Frenzy in Cybercrime
MentionsAnthropic
Runs 2:49:02. Streams from pdst.fm only when you press play.
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-driven cyberattacks. Japan declares a state of cyber-emergency due to attacks.
Show notes from Security Now.
Explained
The technology and terms in this story. Learn more
- TechnologyLLM · Large language modelAn AI model trained on huge amounts of text to understand and generate language, such as ChatGPT or Claude.
- AttackBackdoorA hidden way back into a system that bypasses normal logins.
- TechnologyAI agentAn AI model that acts on its own: it plans steps, uses tools and takes actions, not just answers.