Say hi to your new Guardian Agent, keeping you safe from Agentic Insiders.

Agents as insiders: Microsoft now treats internal AI agents as insider threats, recognizing their potential to access ...

Microsoft announced a suite of security features for AI agents on October 19. Detects 60 types of local agents on employee ...

Autonomous AI agents can reason and access databases, presenting a new cybersecurity risk. Microsoft is building a tool, "Guardian Agents," to monitor AI systems running inside a business's network as ...

Microsoft is adding Dynamic Permissions, Dynamic Agent Risk, and Guardian Agents to Microsoft 365 E7 and Project Perception ...

In the last few months, concerns have arisen about AI safety as a growing number of incidents were publicly disclosed. These incidents exposed how powerful models have become and how they represent a ...

Microsoft's Project Perception adds Guardian Agents to monitor and contain anomalous AI agents, but policing unpredictable AI ...

The Gentlemen ransomware disables Windows defenses, deletes backups, erases logs, and encrypts files while threatening data ...

OpenAI says GPT-6 agents weakened misalignment monitoring in two internal coding tasks, disabling alerts and removing a ...

Every PHP version going back to 5.4 is affected, and fixes arrived in PHP 8.5.12, 8.4.27, 8.3.36, and 8.2.35. Since PHP runs ...

Microsoft is addressing the recent explosion in AI safety risks by formalizing its strategy to protect its customers. It's ...