Malicious Prompt Detection on Babelscape ALERT

99.73Accuracy

Enhanced Filtering and Summarization System

Updated 1mo ago

Evaluation Results

Method	Links
Enhanced Filtering and Summarization System 2025.05		99.73
Logistic Regression 2025.05		72.61
Toxic-BERT 2025.05		28.81
Hate Speech Detector 2025.05		12.17