Introducing MAI-Cyber-1-Flash inside MDASH | Microsoft AI
Today we’re announcing MAI-Cyber-1-Flash inside of MDASH, our multi-agent vulnerability identification and remediation harness. Together they deliver world-class performance at 50% of the cost of leading models.
Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark | Microsoft Security Blog
Today Microsoft is announcing a major step forward in AI-powered cyber defense: a new multi-model agentic scanning harness (codenamed MDASH).
Microsoft Build 2026: Securing code, agents, and models across the development lifecycle | Microsoft Security Blog
Discover how Microsoft enables fast, secure AI development with MDASH and new security capabilities.
Project Perception | Microsoft Security
Project Perception brings agentic security to life with AI agents, multi-agent workflows, and agentic defense. Unlock more with Microsoft Security.
Rethinking security for the age of AI - The Official Microsoft Blog
Editor’s note: Updates with additional details on the model’s crash score. Why security needs a new cyber stack — Introducing Project Perception The physics of cybersecurity are changing. Autonomous systems can now reason, adapt and operate continuously. At the same time, the cost of offense is falling, while the volume, velocity and complexity of what...
Microsoft Agent 365, now generally available, expands capabilities and integrations | Microsoft Security Blog
We’re announcing the general availability of Agent 365, plus previews of new capabilities to discover and manage shadow AI agents. Learn more.
Securing our future: July 2026 progress report on Microsoft's Secure Future Initiative | Microsoft Security Blog
Microsoft’s latest Secure Future Initiative report outlines progress on secure foundations, AI-powered defense, and future-ready cybersecurity.
Securing the Model Context Protocol: Building a safer agentic future on Windows
As AI agents become more capable and integrated into daily workflows, the need for secure, standardized communication between tools and agents has never been greater. At Microsoft Build 2025, we’re announcing an early preview of how Windows 11 is e
Path to Astra: critical capabilities and frontier safeguards
Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.
Microsoft offers devs a better way to control AI agent behavior | TechCrunch
The specification lets developer, compliance, and security teams define their own policies for agents to follow in portable policy files.
Microsoft’s AI Red Team Has Already Made the Case for Itself
Since 2018, a dedicated team within Microsoft has attacked machine learning systems to make them safer. But with the public release of new generative AI tools, the field is already evolving.
Now Meta’s AI agents are going rogue.
One of its AI models accessed the internet and attacked another organization during cybersecurity testing, Anna Dack, Meta’s EMEA head of AI and innovation communications, confirmed in a statement to The Verge. The incident stems from the same basic setup error from testing company Irregular that inadvertently granted Anthropic’s models access to the internet. It only adds to growing concern over the safety of frontier systems. [Link: A Meta AI Model Hacked Another Company During Cybersecurity Testing | https://www.theinformation.com/articles/meta-ai-model-hacked-another-company-cybersecurity-testing | The Information]
Protecting Microsoft at AI speed: How SFI proactively hardens our cloud | Microsoft Security Blog
Learn how Microsoft uses AI to proactively harden its own cloud services through the Secure Future Initiative (SFI).
Five Eyes cyber security agencies statement | Cyber.gov.au
Our joint Five Eyes statement highlights AI is rapidly increasing cyber risk, urging leaders to act now to strengthen resilience, adopt secure practices, and integrate cyber security into core strategy.
OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation
This latest incident is a rather dramatic escalation in agentic AI cybersecurity breaches.
“Paper Trail” Podcast: Microsoft’s “Digital Escorts” Left DOD Vulnerable to Chinese Hackers — ProPublica
A little-known Microsoft program allowed China-based engineers to service the U.S. government’s sensitive computer systems — until reporter Renee Dudley found out about it.
