MITRE ATLAS: community-driven tools for AI security and assurance
Co-hosted with the Kelley School
This presentation focused on the ongoing capability developments and community collaborations around MITRE ATLAS™, a globally accessible, living knowledge base of adversary tactics and techniques based on real-world attack observations and realistic demonstrations from AI red teams and security groups. There are a growing number of vulnerabilities in AI-enabled systems as the incorporation of AI increases the attack surfaces of existing systems beyond those of traditional cyberattacks. ATLAS™ helps raise community awareness and readiness for these unique threats, vulnerabilities, and risks in the broader AI assurance landscape.
Dr. Liaghati discussed the latest community efforts focused on capturing cross-community data on real-world AI incidents in AI security and assurance, growing community understanding of vulnerabilities that can arise when using open-source models or data, building new open-source tools for threat emulation and AI red teaming, and developing mitigations to defend against AI security threats.