Adversarial testing and robustness framework for AI models with 25 attacks (character/word/semantic perturbations, prompt injection, jailbreak, extraction, inversion), defenses (detection/filtering/sanitization), certified robustness metrics, and attack composition.
[email protected] is safe to use (health: 45/100)
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/hex/crucible_adversaryFirst published · 2025-10-11T01:41:44.766635Z
Last updated · 2025-12-29T04:22:20.855772Z