README.md

metadata

license: mit
language:
  - en
tags:
  - cybersecurity
  - vulnerability
  - cwe
  - text-classification
  - fine-tuned
base_model: ehsanaghaei/SecureBERT

SecureBERT — CWE Flat Classifier

        

Part of the CVE-LMTune model suite — language models fine-tuned for multi-taxonomy vulnerability classification.

Paper

Franco Terranova, Sana Rekbi, Abdelkader Lahmadi, Isabelle Chrisment. Multi-Taxonomy Vulnerability Classification with Hierarchically Finetuned Language Models. The 23rd Conference on Detection of Intrusions and Malware & Vulnerability Assessment (DIMVA '26).

Task

CWE (Common Weakness Enumeration) — flat multi-label classification

Performance

Micro-F1 = 0.8114 (best fold, threshold 0.5)

Model Structure

flat

Quick Start

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("Sana9/securebert-cwe-flat")
model = AutoModelForSequenceClassification.from_pretrained("Sana9/securebert-cwe-flat")
model.eval()

text = "Buffer overflow vulnerability in OpenSSL allows remote attackers to execute arbitrary code."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    logits = model(**inputs).logits
    probs = torch.sigmoid(logits)   # multi-label → sigmoid

Note for hierarchical models: This repo contains multiple sub-folders (master + slave models). Load each sub-folder separately using from_pretrained("Sana9/securebert-cwe-flat/master") etc.

Citation

@inproceedings{terranova2026cvelmtune,
  title     = {Multi-Taxonomy Vulnerability Classification with Hierarchically Finetuned Language Models},
  author    = {Terranova, Franco and Rekbi, Sana and Lahmadi, Abdelkader and Chrisment, Isabelle},
  booktitle = {Proceedings of DIMVA '26},
  year      = {2026}
}

Related Resources

• 🤗 Full model suite on Hugging Face
• 💻 CVE-LMTune — Training code (GitHub)
• 📦 Zenodo — Data repository
• 📦 Zenodo — Code repository

Disclaimers

• This product uses the NVD API but is not endorsed or certified by the NVD.
• This project relies on data publicly available from the CWE, CAPEC, and MITRE ATT&CK projects.
• This work has been partially supported by the French National Research Agency under the France 2030 label (Superviz ANR-22-PECY-0008). The views reflected herein do not necessarily reflect the opinion of the French government.