Privacy-Preserving Ml Validation
Objective
Enable safe data sharing for model training.
Control / requirement
Differential privacy + membership inference testing.
Business impact
Without privacy-preserving ML, training data can be reconstructed from model outputs, violating data subject privacy and triggering regulatory action.
Validation approach
Test ID: D5-CTL-06-VTS-001 Test Type: Automated Test Design: Verify DP epsilon value; test membership inference attack success rate Execution Steps: 1. Extract DP epsilon from training config 2. Run membership inference test suite 3. Calculate attack success rate 4. Compare to 50% baseline Pass Criteria: dp_epsilon ≤ 8 (Optimized: ≤ 1.0); membership_inference_success_rate < 55%; dp_training_documented = True Independent Verification: Auditor re-runs membership inference tests.
Expected evidence
Not separately specified in the available source.
Mapping and source
Not separately specified in the available source.
Implementation guidance
Translate the requirement into system-specific procedures, responsible roles, technical configurations and review conditions. Retain evidence showing both design and operating performance. Where the source provides no separate implementation instruction, do not infer that a single technical mechanism is sufficient.
Assessment considerations
- Confirm scope and applicability.
- Inspect control design and responsible ownership.
- Test representative operation and adverse conditions where appropriate.
- Evaluate evidence provenance, completeness and contradictory evidence.
- Record limitations and notably absent outcomes.