Security Now (Audio)

SN 1100: Booby Trapping LLMs - AI Frenzy in Cybercrime

SN 1099: An Alien Mind - From RSA Weakness to Agentic Attacks

SN 1098: How worried should we be? - Unpredictable Agents

The rapid proliferation of agentic AI, exemplified by Meta’s Muse and OpenAI’s new tools, introduces significant security vulnerabilities and unpredictable behaviors. While these agents offer powerful automation, they often bypass standard operating system protections, leading to unauthorized data access and potential ...

SN 1097: Mega Patch Tuesday Fallout - When AI Outsmarts Its Makers

SN 1096: Are we the Krell? - 153 Million Driver's Licenses Leaked

SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race

SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?

SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist

SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails

SN 1091: The Post BlackHat State of AI - When AI Writes Malware

SN 1090: Black Hat - The Hidden Flaws in AI Security Nobody Saw Coming

SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines

SN 1088: A Nefarious Novel Use for AI - Ransomware Negotiations Go High-Tech

SN 1087: HalluSquatting, GhostApproval & GitLost - Patch Tuesday Breaks Records

SN 1086: The Apex Agentic Adversary - Visual Prompt Injection Strikes

SN 1085: A SOTA State-Sponsored Campaign - AI's New Superpower: Loop Engineering

SN 1084: The Residential Proxy Threat - Malicious Proxies in Your Living Room

SN 1083: Patch Tuesday à la AI - Arch Linux Repo Under Siege

SN 1082: The Malicious Use of AI - Anthropic's Red Team Report

SN 1081: AI Captured the Flag - Personal AI: Productivity Superpower or Privacy Threat?