List your company

Abnormal Behavior Detection on JailBreakV (test)

100AccuracyAbnorDetector-Full
88.903291.784194.66597.5459Apr 1, 2025

Evaluation results

MethodLinks
AbnorDetector-FullBase Model=Llama-2-7b-chat, alpha (α)=0.25, beta (β)=0.252025.04100099.5
AbnorDetector-FullBase Model=Llama-2-7b-chat, alpha (α)=0.125, beta (β)=0.1252025.04100099.5
AbnorDetector-FullBase Model=Llama-3.1-70B-Instruct, alpha (α)=0.25, beta (β)=0.252025.041000100
AbnorDetector-FullBase Model=Llama-3.1-70B-Instruct, alpha (α)=0.125, beta (β)=0.1252025.041000100
AbnorDetector-FullBase Model=Llama-3.1-8B-Instruct, alpha (α)=0.25, beta (β)=0.252025.0499.330.222299.33
AbnorDetector-LiteBase Model=Llama-2-7b-chat, alpha (α)=0.5, beta (β)=0.52025.0498.670.222298.83
AbnorDetector-LiteBase Model=Llama-2-7b-chat, alpha (α)=0.25, beta (β)=0.252025.0498.670.222299.17
AbnorDetector-LiteBase Model=Llama-3.1-70B-Instruct, alpha (α)=0.5, beta (β)=0.52025.04980.666798
AbnorDetector-FullBase Model=Gemma-7b-it, alpha (α)=0.25, beta (β)=0.252025.0496.670.222297.48
AbnorDetector-FullBase Model=Llama-3.1-8B-Instruct, alpha (α)=0.125, beta (β)=0.1252025.0495.6722.888997.62
AbnorDetector-LiteBase Model=Llama-3.1-70B-Instruct, alpha (α)=0.25, beta (β)=0.252025.0495.330.222296.46
AbnorDetector-LiteBase Model=Gemma-7b-it, alpha (α)=0.25, beta (β)=0.252025.0495093.6
AbnorDetector-LiteBase Model=Gemma-7b-it, alpha (α)=0.5, beta (β)=0.52025.0493.331.555694.43
AbnorDetector-FullBase Model=Gemma-7b-it, alpha (α)=0.125, beta (β)=0.1252025.049212.666795.34
GradSafeBase Model=Llama-2-7b-chat2025.0491——
AbnorDetector-LiteBase Model=Llama-3.1-8B-Instruct, alpha (α)=0.5, beta (β)=0.52025.0490.672.888994.12
AbnorDetector-LiteBase Model=Llama-3.1-8B-Instruct, alpha (α)=0.25, beta (β)=0.252025.0489.331.555689.93