No Model Access Scans
This page provides an introduction to scans that are configured and run based on prior model predictions and actual outcomes when there is no direct access to the model.
Configuration for scans with no model access may be completed using:
- The Scan Manager UI (for Enterprise users)
- A scan definition (YAML file)
- The publicly available (for Toolkit and Enterprise users) No Model Access Notebook
Configuration Specifications
- In the scan definition
evaluation.no_model_access
is set to true. (by default it is False). - One and only one model is identified in the scan definition.
- Model metadata is required for Scan Manager to store and manage all use cases and scans. (
model_name
,model_id
, andmodel_type
) - The model config may specify a predict_url or a local model, but it is not called during runtime
- Model metadata is required for Scan Manager to store and manage all use cases and scans. (
- Explanation Type is set to
counterfactuals
. - Report Type selections are restricted.
- Dataset schema must specify
outcome
andpredicted_outcome
columns. - Evaluation dataset must specify the
predicted_outcome
column.
Report Types
No model access scans reports are run using an alternative counterfactual method based on predicted outcomes and ground truth provided in the datasets.
Because the standard Genetic algorithm is not used some scan report types are NOT available for no Model access scans including:
- Fast Explanations
- Preflight scans
- SHAP
- Fairness - burden-based metrics
- Robustness
The following reports may be configured for no Model access scans provided the datasets contain the required attributes.
Fairness (ground_truth, predicted_outcome)
- demographic_parity
- disparate_impact
- equal_opportunity
- equal_odds
- sufficiency
Performance (ground_truth, predicted_outcome)
Explanations (predicted_outcome in the Explanation dataset)
Info
Certifai also supports running counterfactual sampling using the ground truth column instead of predicted outcome. However that feature is tangential to the 'no_model_access' scan type, and is only the case when:
- No models are accessed in the scan definition.
- Sampling is specified for explanation scans (i.e. scan.run_explain(sampling=True)).
Counterfactuals for no Model access
Without model access, Certifai is limited in its capabilities to find Counterfactuals explanations because model predictions are not available for data points outside the provided datasets. For this reason, Certifai is unable to run Counterfactual based analyses where the measured score is highly dependent on finding optimal Counterfactuals (i.e. Robustness, Explainability, and burden based Fairness).