Modelpublic

protectai/codebert-base-Malicious_URLs-onnx

sourceHugging Faceupdated 2mo agoView on Hugging Face

5likes943downloads

Model Card

[!WARNING] THIS PROJECT HAS BEEN ARCHIVED. This project and its associated code on GitHub are no longer under active development or maintained.

ONNX version of DunnBC22/codebert-base-Malicious_URLs

This model is a conversion of [DunnBC22/codebert-base-Malicious_URLs](https://huggingface.co/DunnBC22/codebert-base-Malicious_URLs) to ONNX format. It's based on the CodeBERT architecture, tailored for the specific task of identifying URLs that may pose security threats. The model was converted to ONNX using the 🤗 Optimum library.

Model Architecture

Base Model: CodeBERT-base, a robust model for programming and natural languages.

Dataset: https://www.kaggle.com/datasets/sid321axn/malicious-urls-dataset.

Modifications: Details of any modifications or fine-tuning done to tailor the model for malicious URL detection.

Usage

Loading the model requires the 🤗 Optimum library installed.

python

from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import AutoTokenizer, pipeline


tokenizer = AutoTokenizer.from_pretrained("laiyer/codebert-base-Malicious_URLs-onnx")
model = ORTModelForSequenceClassification.from_pretrained("laiyer/codebert-base-Malicious_URLs-onnx")
classifier = pipeline(
    task="text-classification",
    model=model,
    tokenizer=tokenizer,
    top_k=None,
)

classifier_output = classifier("https://google.com")
print(classifier_output)

LLM Guard

Malicious URLs scanner

Community

Join our Slack to give us feedback, connect with the maintainers and fellow users, ask questions, or engage in discussions about LLM security!