UK AI Cyber Security Code of Practice

Secure maintenance (Principles 11 and 12) – UK AI Cyber Security Code of Practice

UK AI Cyber Security Code of Practice 12.3: Monitor internal states of the AI system where useful for security

What does 12.3 require?

Where developers and system operators feel that monitoring the internal states of an AI system would help address security threats or support future security analytics, system operators and developers should do so.

Maintained by Gerard Blokdyk

Other controls in Secure maintenance (Principles 11 and 12) – UK AI Cyber Security Code of Practice

11.1 Provide security updates and patches, with contingency where updates are impossible
11.2 Treat major updates as a new version and support operators through model changes (11.2 and 11.3)
12.1 Log system and user actions
12.2 Analyse logs for anomalies, breaches and unexpected behaviour
12.4 Monitor model and system performance over time for security-relevant change

Query this from an agent

The graph holds this control, the 0 it maps to, and the evidence behind each claim, over MCP and REST.

MCP endpoint All UK AI Cyber Security Code of Practice controls