Microsoft has introduced a series of security tools and capabilities focused on AI-driven vulnerability discovery, AI agents, and AI models. The updates include a multi-agent vulnerability discovery system, new controls for managing and securing AI agents, data protection capabilities, and tools designed to identify potentially vulnerable or compromised AI models before deployment. MDASH targets exploitable vulnerabilities Microsoft expanded the preview of MDASH, a multi-model agentic vulnerability discovery system that now integrates with Microsoft Defender. The … More
The post Microsoft responds to security challenges facing code, AI agents, and models appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
Autonomous AI-driven worm can reason its way through corporate networks
Only 11% of production agents pass the AI agent security bar
Microsoft Scout agent opens a new category of always-on Autopilots