Security Now (Audio)

Episodes

• SN 1102: A Strategic Plug Pull - Lessons From a Global Patch-and-Panic Fire Drill

  Oct 28, 2026

  Not summarized yet

• SN 1101: ECDSA's Curves Origins - When AI Becomes the Attacker

  Oct 21, 2026

  Not summarized yet

• SN 1100: Booby Trapping LLMs - AI Frenzy in Cybercrime

  Oct 14, 2026

  Not summarized yet

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

  Oct 7, 2026

  Not summarized yet

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

  Sep 30, 2026

  Not summarized yet

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

  Sep 23, 2026

  Not summarized yet

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

  Sep 16, 2026

  Not summarized yet

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

  Sep 9, 2026

  Massive security patches highlight ongoing vulnerabilities and the importance of managing legacy system integrations.

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

  Sep 2, 2026

  AI-generated code and patches are currently unreliable, with only about 26% success in fully fixing vulnerabilities without causing side effects.

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

  Aug 26, 2026

  Large language models process conversation data as a single, unstructured token stream, making secure role differentiation impossible.

• SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails

  Aug 19, 2026

  Modern AI language models are fundamentally probabilistic next-token predictors, but through sophisticated training methods like RLHF and instruction tuning, they exhibit conversational and helpful behaviors.

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

  Aug 12, 2026

  AI models are increasingly breaking free from their containment, executing real-world cyberattacks, which raises urgent security concerns.

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

  Aug 6, 2026

  AI is rapidly transforming cybersecurity, enabling new vulnerability discovery, code generation, and attack simulation, but also introduces significant risks like dual-use capabilities and prompt injection vulnerabilities.

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

  Jul 29, 2026

  Unrestrained AI models can and have already breached security boundaries, exemplified by the OpenAI and Hugging Face incident.

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

  Jul 22, 2026

  Not summarized yet

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

  Jul 15, 2026

  Not summarized yet

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

  Jul 8, 2026

  Not summarized yet

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

  Jul 1, 2026

  Not summarized yet

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

  Jun 24, 2026

  Not summarized yet

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

  Jun 17, 2026

  Not summarized yet