Microsoft Says New Cybersecurity AI Model Helps MDASH Score 95.95% at Half the Cost - The Hacker News
Microsoft has integrated a new cybersecurity-specific AI model into its MDASH platform, claiming a 95.95% success rate on vulnerability testing at half the cost. However, the company's performance claims are difficult to verify against public benchmarks.
Why it matters
The development highlights the rapid advancement of AI in cybersecurity automation while underscoring the challenges of benchmarking proprietary AI performance.
Microsoft has launched its first cybersecurity-specific model inside MDASH , its multi-model vulnerability identification and remediation harness.
The company says MDASH, using MAI-Cyber-1-Flash and GPT-5.4, scored 95.95% on CyberGym. It also claims the configuration costs 50% less than its current best MDASH combination of GPT-5.4, GPT-5.4 mini, and GPT-5.3 Codex. Access is limited to approved MDASH customers through an Azure AI Foundry private preview.
MAI-Cyber-1-Flash is designed to handle up to 90% of MDASH tasks, with GPT-5.4 reserved for the hardest 10%. It is available only inside MDASH, not as a standalone public model or general-purpose application programming interface.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in