Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Jailbreak Defense on HarmBench-28K JailbreakTracer Corpus

99.98Accuracy

Sentra-Guard

94.800896.145497.4998.8346Oct 26, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
99.9899.980.004
97.2597.228.1
2025.10
979710
2025.10
959459