UK AI Cyber Security Code of Practice 6.2: Controls on externally offered APIs against attacks on the AI system

What does 6.2 require?

A developer that exposes an API to outside customers or collaborators applies controls that blunt attacks on the AI system through that API, such as rate limits on model access that make reverse engineering harder and slow any attempt to overwhelm defences and poison the model quickly.

Maintained by Gerard Blokdyk

Other controls in Secure development (Principles 5 to 9) – UK AI Cyber Security Code of Practice

5.1 Comprehensive asset inventory including interdependencies
5.2 Processes and tools to track, authenticate, version and secure AI assets
5.3 Disaster recovery plans tailored to attacks on AI systems
5.4 Protect sensitive data and sanitise inputs, with proportionate protection of weights
6.1 Evaluate access control frameworks for APIs, models, data and pipelines
6.3 Dedicated, segregated environments for development and model tuning
6.4 Publish a clear vulnerability disclosure policy
6.5 AI system incident management plan and recovery plan

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