ETSI EN 304 223 Securing AI 5.2.5-4: Evaluate outputs for leakage of model internals and unintended influence

What does 5.2.5-4 require?

Developers should evaluate model outputs to confirm they do not let system operators or end-users work out non-public details of the model or of its training data, and that they do not hand operators or end-users unintended influence over the system.

Maintained by Gerard Blokdyk

Other controls in Clause 5.2: Secure development (Principles 5 to 9) – ETSI EN 304 223 Securing AI

5.2.1-1 Comprehensive asset inventory including interdependencies
5.2.1-2 Processes and tools to track, authenticate, version and secure AI assets
5.2.1-3 Disaster recovery plans tailored to attacks on AI systems
5.2.1-4 Protect sensitive data and sanitise inputs, with proportionate protection of weights
5.2.2-1 Evaluate access control frameworks for APIs, models, data and pipelines
5.2.2-2 Controls on externally offered APIs against attacks on the AI system
5.2.2-3 Dedicated, segregated environments for development and model tuning
5.2.2-4 Publish a clear vulnerability disclosure policy

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 ETSI EN 304 223 Securing AI controls