Update README.md
Browse files
README.md
CHANGED
|
@@ -1,24 +1,64 @@
|
|
| 1 |
-
|
| 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
from gliner import GLiNER
|
| 4 |
|
| 5 |
-
### Load model directly from Hugging Face
|
| 6 |
model = GLiNER.from_pretrained("selfconstruct3d/AITSecNER", load_tokenizer=True)
|
|
|
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
text = """
|
| 9 |
-
Upon opening Emotet maldocs
|
|
|
|
| 10 |
"""
|
| 11 |
|
| 12 |
-
|
| 13 |
-
labels = [
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
-
|
| 16 |
entities = model.predict_entities(text, labels, threshold=0.5)
|
| 17 |
|
| 18 |
-
|
| 19 |
for entity in entities:
|
| 20 |
-
print(entity[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
-
#### Output:
|
| 23 |
-
#### Emotet => MALWARE
|
| 24 |
-
#### Microsoft => ORG
|
|
|
|
| 1 |
+
# AITSecNER - Entity Recognition for Cybersecurity
|
| 2 |
|
| 3 |
+
This repository demonstrates how to use the **AITSecNER** model hosted on Hugging Face, based on the powerful GLiNER library, to extract cybersecurity-related entities from text.
|
| 4 |
+
|
| 5 |
+
## Installation
|
| 6 |
+
|
| 7 |
+
Install GLiNER via pip:
|
| 8 |
+
|
| 9 |
+
```bash
|
| 10 |
+
pip install gliner
|
| 11 |
+
```
|
| 12 |
+
|
| 13 |
+
## Usage
|
| 14 |
+
|
| 15 |
+
### Import and Load Model
|
| 16 |
+
|
| 17 |
+
Load the pretrained AITSecNER model directly from Hugging Face:
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
from gliner import GLiNER
|
| 21 |
|
|
|
|
| 22 |
model = GLiNER.from_pretrained("selfconstruct3d/AITSecNER", load_tokenizer=True)
|
| 23 |
+
```
|
| 24 |
|
| 25 |
+
### Predict Entities
|
| 26 |
+
|
| 27 |
+
Define the input text and entity labels you wish to extract:
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
# Example input text
|
| 31 |
text = """
|
| 32 |
+
Upon opening Emotet maldocs, victims are greeted with fake Microsoft 365 prompt that states
|
| 33 |
+
“THIS DOCUMENT IS PROTECTED,” and instructs victims on how to enable macros.
|
| 34 |
"""
|
| 35 |
|
| 36 |
+
# Entity labels
|
| 37 |
+
labels = [
|
| 38 |
+
'CLICommand/CodeSnippet', 'CON', 'DATE', 'GROUP', 'LOC',
|
| 39 |
+
'MALWARE', 'ORG', 'SECTOR', 'TACTIC', 'TECHNIQUE', 'TOOL'
|
| 40 |
+
]
|
| 41 |
|
| 42 |
+
# Predict entities
|
| 43 |
entities = model.predict_entities(text, labels, threshold=0.5)
|
| 44 |
|
| 45 |
+
# Display results
|
| 46 |
for entity in entities:
|
| 47 |
+
print(f"{entity['text']} => {entity['label']}")
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
### Sample Output
|
| 51 |
+
|
| 52 |
+
```bash
|
| 53 |
+
Emotet => MALWARE
|
| 54 |
+
Microsoft => ORG
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
## About
|
| 58 |
+
|
| 59 |
+
**AITSecNER** leverages GLiNER to quickly and accurately extract cybersecurity-specific entities, making it highly suitable for tasks such as:
|
| 60 |
+
|
| 61 |
+
- Cyber threat intelligence analysis
|
| 62 |
+
- Incident response documentation
|
| 63 |
+
- Automated cybersecurity reporting
|
| 64 |
|
|
|
|
|
|
|
|
|