Building AI for OT Security: The Dragos Analyst-First Approach
Summary: Dragos outlined an analyst-first approach to AI in OT security, built on models trained from more than a decade of OT-specific telemetry, adversary research, and incident response work, with privacy protection and customer data ownership as stated foundations. The Dragos Platform 3.0 release added AI-assisted vulnerability matching delivered through weekly Knowledge Pack updates, with planned Model Context Protocol support in the Platform API and a Dragos-hosted analyst assistant to follow.
Bottom line: Dragos states that most security analysts are trained in IT, not OT, and positions its AI as a way to bring IT talent to entry-level OT proficiency - a skills gap that otherwise leaves critical infrastructure under-defended. The vendor also acknowledges the industry pattern it says it avoids: AI systems need large training sets, and some vendors use customer data for model improvement without explicit consent or clear disclosure.
Read the original at Dragos Blog ↗
- Topics
- OT / ICS & Critical Infrastructure
- Related
- Siemens RUGGEDCOM APE1808 Cyber Risks · Nov 12, 2026How to Assess OT Incident Response Preparedness Cyber Risks · Nov 10, 2026Three China-Nexus Espionage Campaigns Linked Through Sparrow Malware Ecosystem Cyber Risks · Nov 10, 2026