MMSAFE-Bench

by Ogulcan Aydogan
Multi-modal safety evaluation benchmark for AI systems. Covers 20 hazard categories and 9 attack strategies aligned with MLCommons AI Safety standards.

Fund this project

github.com/ogulcanaydogan/MMSAFE-Bench github.com/ogulcanaydogan/MMSAFE-Bench

License

Tags

Unverified URL

The funding manifest has not provided proof via wellKnown that this link is associated with it. Learn more.

Continue