Security Now (Audio)
Episodes
SN 1099: An Alien Mind - From RSA Weakness to Agentic Attacks
Security Now episode 1099 explores the release of GLM 5.
SN 1098: How worried should we be? - Unpredictable Agents
Steve Gibson discusses the security risks of new AI agents, highlighting a critical zero-day vulnerability in Meta’s Muse that allowed malicious control via voice transcription.
SN 1098: How worried should we be? - Unpredictable Agents
Steve Gibson discusses the security risks of new AI agents, highlighting a critical 0-day vulnerability in Meta’s Muse that allowed unauthorized access to user accounts.
SN 1097: Mega Patch Tuesday Fallout - When AI Outsmarts Its Makers
Steve Gibson and Leo Laport discuss the fallout from Microsoft’s mega Patch Tuesday, which caused significant issues like broken Excel copy-paste.
SN 1097: Mega Patch Tuesday Fallout - When AI Outsmarts Its Makers
Steve Gibson and Leo Laporte discuss the fallout from Microsoft’s Patch Tuesday and the recent AI containment breaches at OpenAI, Anthropic, and Google.
SN 1097: Mega Patch Tuesday Fallout - When AI Outsmarts Its Makers
Steve Gibson and Leo Lapo discuss the fallout from Microsoft’s massive Patch Tuesday, which caused widespread issues like broken Excel copy-paste.
SN 1096: Are we the Krell? - 153 Million Driver's Licenses Leaked
Steve Gibson and Leo Laporte analyze Microsoft’s record-breaking September Patch Tuesday, which included nearly 1,000 security fixes driven by AI,…
SN 1096: Are we the Krell? - 153 Million Driver's Licenses Leaked
Steve Gibson and Leo Laporte analyze Microsoft’s record-breaking September Patch Tuesday, which included nearly 1,000 security fixes driven by…
SN 1096: Are we the Krell? - 153 Million Driver's Licenses Leaked
Steve Gibson and Leo Laporte analyze Microsoft’s record-breaking Patch Tuesday, which fixed nearly 1,000 vulnerabilities, highlighting the challenges…
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 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race
Steve Gibson discusses a record-breaking Patch Tuesday with 973 Windows security fixes and the upcoming mandatory enablement of memory integrity on Windows 11.
SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race
Steve Gibson opens with a record-breaking Patch Tuesday, noting 973 Windows security fixes and the upcoming default enablement of memory integrity for all qualifying Windows 11 systems.
SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?
Steve Gibson discusses the inherent security flaws in AI, explaining why LLMs are susceptible to prompt injection and proposing a solution where a…
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 discuss a new research paper revealing that LLMs are inherently insecure due to "role confusion," which makes prompt injection attacks nearly impossible to prevent.
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.