How to meet it
OWASP AISVS v1.01
Monitoring, Logging & Anomaly Detection · Model, Data, and Performance Drift Detection
Detect drift in inputs
Verify that data drift detection monitors input distribution changes that may impact model performance, using statistically validated methods matched to the input data type (e.g., KS test or PSI for tabular numeric features, embedding-distance metrics for text or image).
OWASP AISVS v1.01, requirement 12.3.1
In plain English
Monitor whether the inputs reaching your model are changing in ways that could affect its behaviour, using statistical tests suited to the data type.
What good looks like
- Input distributions are compared with a baseline on a schedule.
- Methods suit the data type.
- Significant drift raises an alert.
How teams usually do it
- KS tests or PSI for numeric features, and embedding-distance metrics for text or images.
Evidence an auditor would accept
- Monitoring configuration and drift reports.
Common mistakes
- Setting a baseline once and never updating it after legitimate changes.
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.