Enhancing AI security through global AI red teaming

In this article Building a global alliance What the research focuses on Why this matters Most AI safety testing still happens inside the walls of individual organizations. That has resulted in a fundamental disconnect: many of the highest-risk failure modes in modern AI systems require deep domain expertise, multilingual context, or regional understanding that no single internal team can fully replicate on its own. As frontier models become more capable, the attack surface expands with them. AI red teaming is no longer just about prompt injection or content safety edge cases. It increasingly involves security operations, misuse scenarios, multilingual harms, alignment failures, and domain-specific abuse patterns that can vary significantly across geographies and languages. Microsoft’s AI Red Team has observed that meaningful testing of advanced AI systems- and models similarly requires broader participation from researchers and practitioners who operate outside traditional corporate security boundaries. To address that gap, today we are announcing the External Red Team Alliance (EXTRA), a formalized global extension of Microsoft’s AI Red Team designed to support and encourage external expertise to advance AI safety and security testing. We are proud to share we are funding the development of new AI safety assessments on six continents through unrestricted gifts. Building a global alliance EXTRA is a two-part initiative focused on expanding AI safety research and strengthening external collaboration. The first component supports a global academic network focused on advancing AI safety and security research. Microsoft’s AI Red Team has provided unrestricted gifts to 18 university labs spanning six continents. The goal is intentionally broad: support researchers who are already investigating difficult, unresolved questions in AI safety and help them continue pushing that work forward independently. Some of the supporting institutions include: Carnegie Mellon University Security and Privacy Institute (CyLab) , United States Georgetown University – Georgetown Security Lab (SecLab) , United States Harvard University Berkman Klein Center for Internet Society (BKC) , United States Howard University Research Institute for Tactical Autonomy (RITA) , United States Indian Institute of Technology Madras – Centre for Responsible AI (CeRAI) , India Korea Advanced Institute of Science Technology – KAIST Web Security Privacy (WSP) Lab , Korea New York University – NYU Alignment Research Group (ARG) , United States Northeastern University Network and Distributed Systems Security (NDS2) Lab, United States University College London – UCL Information Security Research Group (UCL ISec) , United Kingdom University of Cagliari Pattern Recognition and Applications (PRA) Lab , Italy University of California – Berkeley Risk and Security Lab; Center for Responsible, Decentralized Intelligence (CRDI) , United States University of Melbourne Artificial Intelligence Assurance L