Work on the incident sharing initiative is part of the Center’s Secure AI project, built around MITRE ATLAS and kicked off in June.
Goal of the AI Incident Sharing initiative is to improve the collective awareness of threats, and ultimately defense of AI-enabled systems, by enabling the rapid and protected sharing of information about attacks or accidents that involved AI-enabled systems.
The initiative builds on two years of incident sharing collaboration across the broader MITRE ATLAS community to enable more rapid characterization and sharing of anonymized incidents.
In parallel, the Secure AI collaboration also extended the ATLAS threat framework to further update the adversarial threat landscape for generative AI-enabled systems.
Furthermore, much like MITRE ATT&CK, the ATLAS threat framework is a community knowledge base of adversary behaviors that security professionals, developers, and operators use as they protect AI-enabled systems.
Additionally, the project added several new generative AI-focused case studies and attack techniques to the public ATLAS knowledge base as well as new methods to mitigate attacks on AI-enabled systems.
MITRE previously collaborated with Microsoft to begin increasing the ATLAS knowledge base focus on generative AI with updates released in November 2023. This effort continues to keep ATLAS representative of the latest demonstrated threats to AI systems in the wild.
Collaborators on the Secure AI project include: AttackIQ, BlueRock, Booz Allen Hamilton, CATO Networks, Citigroup, Cloud Security Alliance, CrowdStrike, FS-ISAC, Fujitsu, HCA Healthcare, HiddenLayer, Intel, JPMorgan Chase Bank, Microsoft, Standard Chartered, and Verizon Business.
“As public and private organizations of all sizes and sectors continue to incorporate AI into their systems, the ability to manage potential incidents is essential,” said Douglas Robbins, vice president, MITRE Labs. “Standardized and rapid information sharing about incidents will allow the entire community to improve the collective defense of such systems and mitigate external harms.”
Moreover, under the MITRE ATLAS AI Incident Sharing initiative, a community of trusted contributors receive protected and anonymized data on real-world AI incidents occurring across operational AI-enabled systems.
Furthermore, anyone can submit an incident via the public incident sharing site. Upon submission, their organization will end up considered for membership in the trusted community of data receivers. Sharing and receiving this protected information will enable more data-driven risk intelligence and analysis at scale across the community.
Click here for AI incident sharing website and submission form.

