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

Jailbreak Detection on JBB-Behaviors Benign

99.96Accuracy

Sentra-Guard

94.96297.46199.96102.459Oct 26, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
2025.10
99.9699.9899.9499.960