Data

Tools

Indexes

Applications

Experiments

Open Source Science

kg-cybersec

https://github.com/garima0106/kg-cybersec

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: garima0106
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 6.97 MB
Statistics
  • Stars: 1
  • Watchers: 2
  • Forks: 2
  • Open Issues: 1
  • Releases: 0
Created over 3 years ago · Last pushed about 2 years ago
Metadata Files
Readme Citation

README.md

KG-Cybersec

In this project, we developed an ontology framework and knowledge graphs for teaching cybersecurity courses. The data is available as unstructured text in lab manuals and course material. There is no standrad datasets available for cybersecurity.

NER

We used NER to extract the raw entities as subjects and objects in a sentence and relations as the root of the sentence. We store these as triples and generated prelim knowledge graphs from the extracted information.

Ontology Development

We then used domain knowledge to design an ontology framework for cybersecurity education and refined the extracted entities and relations. The key entity catgories and their types were identified. The key relations were also identified and an attribute called, 'action' was added to relations. We then developed the knowledge graph from final triples.

Entity Matcher

The custom entity matcher program can be used to run on other documents and identify the entities given in its KB file, kbcyber.yaml. The lexical analyser lexcyber.yaml helped in entity linking and scope resolution. The module Entity Matchher contains the code in pythonscrript EntitymatchercyberSec.py and the entity KB data is available in yaml files

ChatBot

We built an intent classification chatbot using SVM based on key entities identified. The Module ChatBot contains the model, json file for responses and API implementation.

Owner

  • Name: Garima
  • Login: garima0106
  • Kind: user
  • Location: Arizona
  • Company: Arizona State University

Citation (citation.cff) 

@misc{KG-cybersecurity-education2022,
  author = {Garima Agrawal},
  title = {{KG for Cybersecurity Education}},
  url = {https://github.com/garima0106/KG-Cybersec.git},
  publisher = {GitHub},
  year = {2022}
}

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Dependencies

requirements.txt pypi
  • Jinja2 *
  • MarkupSafe ==2.0.1
  • Pillow *
  • PyYAML ==5.4.1
  • anyio ==3.3.4
  • asgiref ==3.4.1
  • certifi ==2021.10.8
  • charset-normalizer ==2.0.7
  • click ==8.0.3
  • cycler ==0.10.0
  • dnspython ==2.1.0
  • email-validator ==1.1.3
  • fastapi *
  • h11 ==0.12.0
  • httptools ==0.2.0
  • idna ==3.3
  • itsdangerous ==2.0.1
  • joblib ==1.2.0
  • kiwisolver ==1.3.2
  • matplotlib ==3.4.3
  • nltk *
  • numpy *
  • orjson ==3.6.4
  • pandas ==1.3.4
  • pydantic ==1.8.2
  • pyparsing ==3.0.3
  • python-dateutil ==2.8.2
  • python-dotenv ==0.19.1
  • python-multipart ==0.0.5
  • pytz ==2021.3
  • regex ==2021.10.23
  • requests ==2.26.0
  • scikit-learn ==1.0.1
  • scipy *
  • seaborn ==0.11.2
  • six ==1.16.0
  • sklearn ==0.0
  • sniffio ==1.2.0
  • starlette *
  • threadpoolctl ==3.0.0
  • tqdm ==4.62.3
  • typing-extensions ==3.10.0.2
  • ujson *
  • urllib3 *
  • uvicorn ==0.15.0
  • uvloop ==0.16.0
  • watchgod ==0.7
  • websockets ==10.0