Update README.md

README.md

@@ -1,50 +1,68 @@
 ---
 library_name: transformers
-license: mit
+license: cc-by-4.0
 base_model: roberta-base
-tags:
-- generated_from_trainer
 metrics:
 - accuracy
+tags:
+- generated_from_trainer
+- text-classification
+- classification
+- nlp
+- vulnerability
 model-index:
 - name: vulnerability-severity-classification-roberta-base
   results: []
+datasets:
+- CIRCL/vulnerability-scores
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
-# vulnerability-severity-classification-roberta-base
+# VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
+
+# Severity classification
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the dataset [CIRCL/vulnerability-scores](https://huggingface.co/datasets/CIRCL/vulnerability-scores).
+
+The model was presented in the paper [VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification](https://huggingface.co/papers/2507.03607) [[arXiv](https://arxiv.org/abs/2507.03607)].
+
+**Abstract:** VLAI is a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated into the Vulnerability-Lookup service.
+
+You can read [this page](https://www.vulnerability-lookup.org/user-manual/ai/) for more information.
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.0430
-- Accuracy: 0.8132
-- F1 Macro: 0.7438
-- Low Precision: 0.6379
-- Low Recall: 0.5097
-- Low F1: 0.5666
-- Medium Precision: 0.8494
-- Medium Recall: 0.8632
-- Medium F1: 0.8562
-- High Precision: 0.8038
-- High Recall: 0.8062
-- High F1: 0.8050
-- Critical Precision: 0.7484
-- Critical Recall: 0.7460
-- Critical F1: 0.7472
 
 ## Model description
 
-More information needed
+It is a classification model and is aimed to assist in classifying vulnerabilities by severity based on their descriptions.
+
+## How to get started with the model
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+labels = ["low", "medium", "high", "critical"]
+
+model_name = "CIRCL/vulnerability-severity-classification-roberta-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+model.eval()
 
-## Intended uses & limitations
+test_description = "SAP NetWeaver Visual Composer Metadata Uploader is not protected with a proper authorization, allowing unauthenticated agent to upload potentially malicious executable binaries \
+that could severely harm the host system. This could significantly affect the confidentiality, integrity, and availability of the targeted system."
+inputs = tokenizer(test_description, return_tensors="pt", truncation=True, padding=True)
 
-More information needed
+# Run inference
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
 
-## Training and evaluation data
+# Print results
+print("Predictions:", predictions)
+predicted_class = torch.argmax(predictions, dim=-1).item()
+print("Predicted severity:", labels[predicted_class])
+```
 
-More information needed
 
 ## Training procedure
 
@@ -59,6 +77,23 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 5
 
+It achieves the following results on the evaluation set:
+- Loss: 2.0430
+- Accuracy: 0.8132
+- F1 Macro: 0.7438
+- Low Precision: 0.6379
+- Low Recall: 0.5097
+- Low F1: 0.5666
+- Medium Precision: 0.8494
+- Medium Recall: 0.8632
+- Medium F1: 0.8562
+- High Precision: 0.8038
+- High Recall: 0.8062
+- High F1: 0.8050
+- Critical Precision: 0.7484
+- Critical Recall: 0.7460
+- Critical F1: 0.7472
+
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Macro | Low Precision | Low Recall | Low F1 | Medium Precision | Medium Recall | Medium F1 | High Precision | High Recall | High F1 | Critical Precision | Critical Recall | Critical F1 |