MDASH
Coverage of MDASH in the Nexus archive.
- Microsoft and Wiz mind-meld agents catch more than 90% of bugs
Microsoft and Wiz's agentic bug-hunting systems, MDASH and Project Atlas, achieved over 90% success rates in identifying software vulnerabilities on CyberGym, outperforming models from OpenAI, Anthropic, and Google. Both systems use multi-model architectures to optimize vulnerability detection and remediation, with Wiz planning to add a third model to Atlas.
- Microsoft Says New Cybersecurity AI Model Helps MDASH Hit 95.95% at Half the Cost
Microsoft has launched a new cybersecurity-specific AI model in MDASH, achieving a 95.95% score on CyberGym with a configuration that costs 50% less than its previous best setup.
- Microsoft debuts AI cybersecurity offerings as competition heats up
Microsoft introduced MAI-Cyber-1-Flash, an AI-powered cybersecurity model integrated into its MDASH tool and Project Perception platform, claiming superior performance and cost efficiency over competitors like Mythos, Gemini, and GPT. The model scored 96% on the CyberGym benchmark, 12 percentage points higher than the next best, and is set for public release on August 3. Microsoft emphasized safety, third-party validation, and cost reduction, with CEO Satya Nadella highlighting the system's specialized design.
- Microsoft Says MDASH Beats Claude Mythos and GPT-5.6 Sol in Cybersecurity Test
Microsoft claims its new cyber model, MDASH, outperforms Claude Mythos and GPT-5.6 Sol in a cybersecurity test. The model enables over 100 AI agents to identify software flaws at half the cost of the current MDASH configuration.
- Microsoft discloses ‘the mother of all’ vulnerability loads, tripling June’s previous record
Microsoft disclosed 622 vulnerabilities in its June Patch Tuesday update, tripling the previous record of 206. The surge reflects increased use of AI tools like Microsoft’s MDASH to detect defects at scale. Experts warn the volume may exceed 3,000 CVEs in 2026, though most may not pose immediate risks.
- Welcome to the vulnpocalypse, as vendors use AI to find bugs and patches multiply like rabbits
Palo Alto Networks used AI to scan its codebase and found 75 security holes, while Microsoft's AI-powered bug hunting system MDASH found 17 vulnerabilities. This increase in vulnerability detection is expected to lead to more patches and work for admins. The use of AI in bug hunting is becoming more prevalent among security vendors.
- Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday
Microsoft has introduced MDASH, a multi-model AI system for vulnerability discovery and remediation. The system is being tested by some customers as part of a limited private preview. MDASH has already found 16 Windows flaws that were fixed in Patch Tuesday.
- Doozy of a Patch Tuesday includes 30 critical Microsoft CVEs
Microsoft released fixes for 137 CVEs, including 30 critical flaws, with 14 earning a 9.0 or higher CVSS severity rating. The company's AI bug hunting system, MDASH, found 16 of the vulnerabilities addressed in this month's release. Microsoft admins are expected to face a lot more work in applying and testing the patches.