topic
SOC
2 posts tagged “SOC”.
Project Perception: Microsoft's agentic security moves from alerting to acting
Microsoft's Project Perception coordinates red, blue, and green AI agents on a new cyber stack powered by MAI-Cyber-1-Flash. What shipped in the public preview, what's gated behind human approval, how the architecture fits together, and the questions worth testing before you rely on it.
Once a prompt injection reaches the AI, does it obey? I tested that too
Part 2 of a defensive-research series: once a planted instruction reaches an AI SOC-triage assistant, how often does it obey? Measured across two models and four defence conditions — with the finding that instructing the reader beats fancy ingestion tags, and that tags can backfire on cheap models.