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

About this episode

The episode discusses the hidden flaws in AI security revealed at Black Hat Las Vegas, exploring both the innovations and exploits associated with AI technology.

At Black Hat Las Vegas, the Security Now crew digs into how AI is not just finding hidden software bugs but also fueling both groundbreaking innovation and alarming new exploits. When open models can launch surprise Bitcoin heists, who draws the line between forbidden knowledge and genuine progress? • Black Hat and DEF CON: Hacking Stories and Conference Culture • Zoox Ride-Hailing Hack and Over-the-Air Vulnerabilities • Autonomous Vehicles, AI, and the Security Implications • Hosts Share Personal Adoption and Use of AI Tools • AI-Powered Coding: From Hobbyists to Advanced Agency Chains • Local Models vs. Cloud AI: Privacy, Cost, and Control • App Development Democratized: Listeners Build Custom Solutions With AI • Code Generation, Testing, and Managing AI-Driven Project Cycles • AI's Role in Security: Vulnerability Discovery, Exploitation, and Patch Challenges • Technical Debt and the Race to Patch Decades-Old Bugs • The Dual-Use Dilemma: AI Tools for Both Attack and Defense • Guardrails, Model Partitioning, and the Fight Over Forbidden Knowledge • Open vs. Restricted AI: Global Models, Distillation, and Free Speech • LLM Security Weaknesses: Prompt Injection and Role Confusion…

Topics covered

• AI security
• vulnerability discovery
• autonomous vehicles
• hacking culture
• AI tools
• privacy and control

Keywords

• AI
• security
• Black Hat
• vulnerabilities
• autonomous vehicles
• Bitcoin heists
• coding
• privacy
• technical debt
• dual-use dilemma

Mentioned in this episode

Organizations: Black Hat, DEF CON, Zoox, AI, Bitcoin

More episodes of Security Now (Audio)

• SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race · September 9, 2026 · 3h 6m
• SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code? · September 2, 2026 · 2h 52m
• SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist · August 26, 2026 · 2h 48m
• SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails · August 19, 2026 · 2h 49m
• SN 1091: The Post BlackHat State of AI - When AI Writes Malware · August 12, 2026 · 2h 51m
• SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines · July 29, 2026 · 3h 8m