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

Jailbreak Detection on Jailbreak V28K

96.4AUROC

MTK

57.08867.29477.587.706Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
96.4-----
2026.06
94.9-----
2026.06
93.8-----
2026.06
88.1-----
2026.06
86.6-----
2026.06
82.3-----
2026.06
71.2-----
2026.06
62.8-----
2026.06
62.7-----
2026.06
61.1-----
2026.06
60.7-----
2026.06
60.7-----
2026.06
59.8-----
2026.06
58.6-----
2025.10
-99.9199.9399.8899.90.9
2025.10
-99.9810099.9799.980.4