A small prompt-injection detector that catches injections hidden in emails, and where it still fails
TL;DR. I trained a 142M param classifier (DeBERTa-v3-small) to detect prompt injections before an agent uses them, and tested it only on attack sources it hadn't seen before. On the model sample injections concealed in emails (the LLMail-Inject benchmark), it achieves an F1 0.88 (versus 0.57 for protectai/deberta-v3-base-prompt-injection-v2, a popular...
Oct 61