How to meet it
OWASP AISVS v1.01
Adversarial Robustness · Model-Extraction Defense
Watermark or fingerprint the model
Verify that model watermarking or fingerprinting techniques are applied so that unauthorized copies can be identified.
OWASP AISVS v1.01, requirement 11.3.3
In plain English
Watermark or fingerprint your model so you can recognise a stolen copy.
What good looks like
- A watermark or fingerprint is embedded in the model or its outputs.
- There is a documented way to test a suspect model.
- The method survives fine-tuning to a reasonable degree.
How teams usually do it
- Training-time watermarks or trigger sets known only to you.
Evidence an auditor would accept
- The method and test results.
Common mistakes
- A watermark that is never tested on a modified copy.
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.