This model is a fine-tuned version of
microsoft/mdeberta-v3-base on a combination of
jackhhao/jailbreak-classification,
deepset/prompt-injections, a custom datasets containing known attacks, and injections nested in legitimate content like websites and articles.
1from transformers import pipeline
2
3classifier = pipeline(
4 "text-classification",
5 model="proventra/mdeberta-v3-base-prompt-injection"
6)
7
8print(classifier("Your text to scan"))
