metadata

library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
  - prompt-injection
  - injection
  - security
  - llm-security
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: mdeberta-v3-base-prompt-injection
    results: []

mdeberta-v3-base-prompt-injection

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.

Usage

from transformers import pipeline

classifier = pipeline(
  "text-classification",
  model="proventra/mdeberta-v3-base-prompt-injection"
)

print(classifier("Your text to scan"))

Use in Proventra Core

proventra-core python library

check out Proventra