How to meet it
OWASP AISVS v1.01
AI-Assisted Secure Coding (Appendix C) · Continuous Feedback, Adversarial Testing & Model Fine-Tuning
Regression-test every model change
Verify that a closed-loop evaluation harness runs regression tests after every fine-tune, system-prompt change, or model upgrade. Security metrics must meet or exceed the prior baseline before deployment.
OWASP AISVS v1.01, requirement AC.6.4
In plain English
After every fine-tune, system prompt change or model upgrade, rerun a security regression suite. Security results must match or beat the previous version before deployment.
What good looks like
- A regression suite runs automatically on each change.
- Results are compared with the previous baseline.
- Worse results block deployment.
How teams usually do it
- An evaluation job in the tool's configuration pipeline.
Evidence an auditor would accept
- Results per change.
Common mistakes
- Upgrading the model in tool settings with no testing.
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.