23:51
2026-07-13
discuss.huggingface.co
ai-safety
I trained a Prompt Injection Classifier Using a 14M Parameter Discriminator
A prompt injection classifier trained on a 14M-parameter Electra-small discriminator achieves 0.990 F1 and 0.999 ROC-AUC on English WildGuardTest prompt-adversarial classification, but shows edge case…