How to meet it
OWASP AISVS v1.01
Adversarial Robustness · Model Alignment, Safety, and Robustness Testing and Training
Test against known adversarial attacks
Verify that models are evaluated against known adversarial attack techniques relevant to their modality.
OWASP AISVS v1.01, requirement 11.1.3
In plain English
Test the model against attack techniques known for its input type, such as jailbreak prompts for text or adversarial noise for images.
What good looks like
- The test set covers published attack techniques for each input type.
- It is updated as new techniques appear.
- Results are recorded per model version.
How teams usually do it
- Open red-teaming tools and attack libraries for LLMs and vision models.
- Periodic manual red-team exercises.
Evidence an auditor would accept
- The test set and results.
Common mistakes
- Testing with a handful of well-known jailbreaks the model was already trained against.
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.