https://github.com/balnarendrasapa/cybersecurity-ner

Named-Entity-Recognition for Cybersecurity. This repository contains code for fine-tuning a pretrained ner model with custom dataset
https://github.com/balnarendrasapa/cybersecurity-ner

cybersecurity fine-tuning huggingface named-entity-recognition transformers

Last synced: 8 months ago
JSON representation

Named-Entity-Recognition for Cybersecurity. This repository contains code for fine-tuning a pretrained ner model with custom dataset

• Host: GitHub
• URL: https://github.com/balnarendrasapa/cybersecurity-ner
• Owner: balnarendrasapa
• License: gpl-3.0
• Created: 2023-11-19T22:21:09.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2023-12-01T23:32:03.000Z (over 2 years ago)
• Last Synced: 2023-12-02T01:29:47.919Z (over 2 years ago)
• Topics: cybersecurity, fine-tuning, huggingface, named-entity-recognition, transformers
• Language: Jupyter Notebook
• Homepage:
• Size: 323 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Named-Entity-Recognition for Cybersecurity



- This project is about building a NLP model that can be used for Named-Entity-Recognition in the field of Cybersecurity.

- `distilbert-base-uncased` pretrained model was used in this project. This model is fine-tuned for this project's purpose.

- To open the project, Click on the above google colab badge.

## Dataset

- MITRE Dataset is taken to train the model. The dataset is available in this repository as `MITRE.zip`. or Click [here](https://github.com/balnarendrasapa/cybersecurity-ner/raw/readme/MITRE.zip) to download the dataset.

- MITRE dataset is also uploaded to huggingface. click [here](https://huggingface.co/datasets/bnsapa/cybersecurity-ner) to go there.

- You can also import the dataset by running the below code.

```python

from datasets import load_dataset

dataset = load_dataset("bnsapa/cybersecurity-ner")

```

## Metrics

![image](https://github.com/balnarendrasapa/cybersecurity-ner/assets/61614290/ba74fb6c-1348-4d02-951d-2a01a5a018c8)

## Huggingface

- The finetuned model is available on the huggingface. click [here](https://huggingface.co/bnsapa/cybersecurity-ner) to go there.

## Example

I typed `abcde is a computer malware`. I defined the context such that it implies `abcde` is virus and model is able to capture that.

![image](https://github.com/balnarendrasapa/cybersecurity-ner/assets/61614290/b97a37c8-a4d3-464f-a48b-a6adb21dced8)