Microsoft's new vulnerability-scanning system, codenamed MDASH, scored 88.45% on the CyberGym benchmark, surpassing ...
Microsoft MDASH outperforms Mythos Preview on the CyberGym benchmark, demonstrating improved vulnerability discovery ...
100 AI agents worked in unison to discover 16 flaws, including four critical-severity ones.
Microsoft’s new MDASH AI system found 16 Windows vulnerabilities fixed in this month’s Patch Tuesday, including 2 RCE flaws ...
Windows networking and authentication components, including four critical remote code execution bugs patched in this month’s ...
Microsoft unveils MDASH, a multi-model AI cybersecurity system that found critical Windows flaws using over 100 specialized ...
MDASH relies on more than 100 specialized agents to find software bugs. It's being used internally, but Microsoft is also ...
Microsoft has unveiled a new AI-driven vulnerability discovery system that identified 16 previously unknown Windows ...
A new agentic AI security multi-model defense system built by Microsoft's Autonomous Code Security team helped researchers find 16 new vulnerabilities across the Windows networking and authentication ...
Microsoft has joined the ranks of companies using artificial intelligence models to look for vulnerabilities in large ...
Microsoft and Palo Alto Networks have separately reported significant results after turning AI on their own code to find ...
Microsoft has unveiled MDASH, a cybersecurity system powered by more than 100 AI agents that work together to uncover ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results