Upload folder using huggingface_hub

README.md

@@ -3,35 +3,26 @@ license: mit
 language:
 - en
 tags:
+- cybersecurity
+- vulnerability
 - mitre-attack
 - text-classification
 - fine-tuned
-- cybersecurity
-- vulnerability
 - securebert
 base_model: ehsanaghaei/SecureBERT
 ---
 
-# SecureBERT — MITRE ATT&CK Enterprise Subtechniques Flat Classifier
+# SecureBERT — CVE-LMTune ATT&CK Classifier (Flat)
+
+<div align="center" style="display:inline-flex; gap:18px; align-items:center; flex-wrap:nowrap;"> <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/5/5b/Logo_Universit%C3%A9_de_Lorraine.svg/1280px-Logo_Universit%C3%A9_de_Lorraine.svg.png" alt="Universite de Lorraine" style="height:50px; width:auto;" /> <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/9/95/Inr_logo_rouge.svg/1280px-Inr_logo_rouge.svg.png" alt="INRIA" style="height:50px; width:auto;" /> <img src="https://upload.wikimedia.org/wikipedia/fr/6/6e/Logo_loria_abrege_couleur.png" alt="LORIA" style="height:70px; width:auto;" /> <img src="https://www.pepr-cybersecurite.fr/wp-content/uploads/2023/09/pep-cybersecurite-550x250-1.png" alt="SuperViZ" style="height:70px; width:auto;" /> </div>
 
+[![GitHub](https://img.shields.io/badge/GitHub-CVE--LMTune-black?logo=github)](https://github.com/terranovafr/CVE-LMTune)
+[![Paper](https://img.shields.io/badge/Paper-HAL-green?logo=information&logoColor=white)](https://hal.science/hal-05500820)
 [![PhD theses.fr](https://img.shields.io/badge/Project-theses.fr-orange?logo=university&logoColor=white)](https://theses.fr/s371241)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Zenodo Data](https://img.shields.io/badge/Zenodo-Data%20Repository-lightblue?logo=information&logoColor=white)](https://doi.org/10.5281/zenodo.16936476)
-[![Zenodo Code](https://img.shields.io/badge/Zenodo-Code%20Repository-blue?logo=information&logoColor=white)](https://zenodo.org/records/17368476)
-[![GitHub](https://img.shields.io/badge/GitHub-CVE--LMTune-black?logo=github)](https://github.com/terranovafr/CVE-LMTune)
-
-<div align="center">
-  <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/5/5b/Logo_Universit%C3%A9_de_Lorraine.svg/1280px-Logo_Universit%C3%A9_de_Lorraine.svg.png" alt="Universite de Lorraine" height="50"/>
-  &nbsp;&nbsp;
-  <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/9/95/Inr_logo_rouge.svg/1280px-Inr_logo_rouge.svg.png" alt="INRIA" height="50"/>
-  &nbsp;&nbsp;
-  <img src="https://upload.wikimedia.org/wikipedia/fr/6/6e/Logo_loria_abrege_couleur.png" alt="LORIA" height="70"/>
-  &nbsp;&nbsp;
-  <img src="https://www.pepr-cybersecurite.fr/wp-content/uploads/2023/09/pep-cybersecurite-550x250-1.png" alt="SuperViZ" height="70"/>
-</div>
-<br>
 
-Part of the **CVE-LMTune** model suite — language models fine-tuned for multi-taxonomy vulnerability classification.
+Part of the **CVE-LMTune** model suite, a collection of language models fine-tuned for multi-taxonomy vulnerability classification across widely used cybersecurity taxonomies, including CWE, CAPEC, and MITRE ATT&CK.
 
 ## Paper
 
@@ -39,21 +30,34 @@ Part of the **CVE-LMTune** model suite — language models fine-tuned for multi-
 > *Multi-Taxonomy Vulnerability Classification with Hierarchically Finetuned Language Models.*
 > The 23rd Conference on Detection of Intrusions and Malware & Vulnerability Assessment **(DIMVA '26)**.
 
-## Task
+## Overview
+
+This model performs **multi-label ATT&CK classification** from vulnerability descriptions. Given a CVE-style description, it predicts one or more ATT&CK identifiers associated with the described vulnerability.
 
-**MITRE ATT&CK Enterprise Subtechniques flat multi-label classification**
+| Property | Value |
+|----------|-------|
+| Taxonomy | MITRE ATT&CK Enterprise Subtechniques |
+| Task | Multi-label text classification |
+| Input | Vulnerability description (e.g., CVE summary) |
+| Output | One or more ATT&CK identifiers |
+| Number of labels | 175 |
+| Number of samples | 231,009 |
+| Latest CVE update included | 17/06/2025 |
+| Split | train (60%), val (20%), test (20%) |
 
-## Performance (test set)
+## Evaluation Results
 
-| Metric | Score |
-|---|---|
-| Micro-F1 | **0.8168** |
-| LRAP | **0.9152** |
-| Mean Reciprocal Rank | **0.9460** |
+The model was evaluated on the held-out test set using standard multi-label classification metrics using sigmoid activation and a default threshold of 0.5.
 
-## Model Structure
+**Ranking Metrics**
+| LRAP | MRR | Coverage Error | Label Ranking Loss | P@1 | P@3 | P@5 | R@1 | R@3 | R@5 |
+|------|-----|----------------|--------------------|-----|-----|-----|-----|-----|-----|
+| 0.9152 | 0.9460 | 18.79 | 0.0173 | 0.9321 | 0.9084 | 0.8458 | 0.1286 | 0.3779 | 0.5554 |
 
-Flat classifier (single model, multi-label output via sigmoid).
+**Threshold = 0.5**
+| Micro P | Micro R | Micro F1 | Macro F1 | Weighted F1 | Hamming Loss | Subset Accuracy |
+|--------|--------|----------|----------|------------|--------------|----------------|
+| 0.8612 | 0.7767 | 0.8168 | 0.4286 | 0.8093 | 0.0264 | 0.6874 |
 
 ## Quick Start
 
@@ -63,24 +67,34 @@ import torch
 
 tokenizer = AutoTokenizer.from_pretrained("Sana9/securebert-vuln2attack-flat")
 model = AutoModelForSequenceClassification.from_pretrained("Sana9/securebert-vuln2attack-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
+    probs = torch.sigmoid(
+        model(**tokenizer(text, return_tensors="pt", truncation=True)).logits
+    )[0]
+
+predictions = {
+    model.config.id2label[i]: p.item()
+    for i, p in enumerate(probs)
+    if p > 0.5
+}
+
+print(predictions)
 ```
 
 ## Citation
 
 ```bibtex
-@inproceedings{terranova2026cvelmtune,
+@inproceedings{terranova2026multitaxonomy,
+  author    = {Franco Terranova and Sana Rekbi and Abdelkader Lahmadi and Isabelle Chrisment},
   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}
+  booktitle = {Proceedings of the International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment (DIMVA)},
+  year      = {2026},
+  month     = jul,
+  address   = {Chania, Crete, Greece},
+  note      = {HAL identifier: hal-05500820v2}
 }
 ```
 
@@ -89,10 +103,9 @@ with torch.no_grad():
 - 🤗 [Full model suite on Hugging Face](https://huggingface.co/Sana9)
 - 💻 [CVE-LMTune — Training code (GitHub)](https://github.com/terranovafr/CVE-LMTune)
 - 📦 [Zenodo — Data repository](https://doi.org/10.5281/zenodo.16936476)
-- 📦 [Zenodo — Code repository](https://zenodo.org/records/17368476)
 
 ## Disclaimers
 
-- This product uses the NVD API but is not endorsed or certified by the NVD.
+- This product is a result of the use of the NVD API but is not endorsed or certified by the NVD. The same for the CVE2CAPEC project and the Hugging Face API.
 - 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).
+- 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.