AI Security Podcast

Gen AI Threat Modeling vs. AI-Powered Defense:

6 snips
Jul 31, 2025
Join Jackie Bow, the Technical Lead of Threat Detection Engineering at Anthropic, and Kane Narraway, who heads the Enterprise Security Team at Canva, as they dive deep into the dual-edged sword of AI in security. Jackie reveals how AI, specifically Claude, revolutionizes threat detection by breaking traditional barriers. In contrast, Kane emphasizes the risks tied to AI integrations, arguing that many challenges mirror existing vulnerabilities. Together, they explore innovative threat modeling strategies while balancing the need for strong security with the power of AI.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
INSIGHT

AI Amplifies Existing SaaS Risks

  • AI adds multiple layers of risk, increasing the attack surface and overall risk threshold in security environments.
  • These risks are mostly extensions of existing SaaS vulnerabilities but worsen the security challenge.
ADVICE

Harness AI Creativity in Security

  • Use generative AI models like Claude to gain greater visibility and control in threat detection, breaking free from black-box tools.
  • Allow AI to hallucinate creatively within boundaries to uncover investigative paths humans might miss.
ADVICE

Focus on Access and Integrations

  • Focus AI threat modeling on access methods and integrations, as these introduce the highest risks.
  • Prioritize securing data access and authorization to mitigate risk when AI interacts with enterprise systems.
Get the Snipd Podcast app to discover more snips from this episode
Get the app