VulnBERT v8

Vulnerability detection model for Linux kernel commits.

Results

Metric Value
AUC 0.987
Recall 91.4%
Precision 88.4%
F1 0.899
FPR 5.9%

Usage

import torch

checkpoint = torch.load("pytorch_model.pt", map_location="cpu")
model.load_state_dict(checkpoint["model_state_dict"])

Full code: github.com/quguanni/vulnbert

Training

License

MIT

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train pebblebed/vulnbert-v8