Security Now (Audio)
Episodes
SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race
Steve Gibson and Leo Laporte discuss a record-breaking Patch Tuesday with 973 Windows fixes and the upcoming mandatory enablement of Memory Integrity.
SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?
Steve Gibson discusses a new research paper showing that AI models are poor at fixing the vulnerabilities they find, often introducing security flaws.
SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist
Steve Gibson and Leo Laporte explore the fundamental "role confusion" in LLMs that makes prompt injection an inherent, unfixable security flaw.