Attack Success RateNeed for evaluation focused on actual harm Attack Success Rate (ASR) should be measured based on successful information leakage or function call criteria, not just by observing a few prefix words and making quick judgments ASR modelprotectai/distilroberta-base-rejection-v1 · Hugging FaceWe’re on a journey to advance and democratize artificial intelligence through open source and open science.https://huggingface.co/protectai/distilroberta-base-rejection-v1