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

Malicious Prompt Detection on Weighted Average Across All Datasets

98.71Accuracy

Enhanced Filtering and Summarization System

-2.086824.081650.2576.4184May 2, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
98.71
2025.05
90.42
2025.05
4.41
2025.05
1.79