Defense at AI speed: Microsoft’s new multi-model agentic security system finds 16 new vulnerabilities

Today Microsoft is announcing a major step forward in AI-powered cyber defense: a new multi-model agentic scanning harness (codenamed MDASH). The post Defense at AI speed: Microsoft’s new multi-model agentic security system finds 16 new vulnerabilities appeared first on Microsoft Security Blog .

In this article AI-powered vulnerability discovery at hyper-scale Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness Using codename MDASH for security research The 5. 12. 2026 Patch Tuesday cohort Two deep dives CVE-2026-33827—Remote unauthenticated UAF in tcpip. sys via SSRR CVE-2026-33824: Unauthenticated IKEv2 SA_INIT + fragmentation → double-free → LocalSystem RCE How capable is codename MDASH?

What this all means Conclusion Today Microsoft announced a major step forward in AI-powered cyber defense: our new agentic security system helped researchers find 16 new vulnerabilities across the Windows networking and authentication stack—including four Critical remote code execution flaws in components such as the Windows kernel TCP/IP stack and the IKEv2 service.