Threat Modeling for AI Apps with Attacks as Code

Explore the evolving landscape of threat modeling for AI applications in this 25-minute conference talk by Priyanka Tembey and Glenn McDonald from Operant. Delve into the unique security challenges posed by AI and learn how to implement automated threat modeling using the open-source Secops-Chaos framework. Discover how to customize baseline frameworks like OWASP LLM risks and MITRE ATLAS to suit organizational needs, and understand the importance of continuous verification for AI apps built on untrusted third-party models. Gain hands-on experience through demonstrations mapping MITRE ATLAS TTPs to AI applications running in Kubernetes environments, and learn how to integrate threat modeling into the CI/CD pipeline for enhanced security.

Threat Modeling for AI Apps with Attacks as Code - Priyanka Tembey, Operant & Glenn McDonald