webpage-phishing-detection

Machine Learning based spam website detection

try heroku app

---

Original work by:

Hannousse, Abdelhakim; Yahiouche, Salima (2021), “Web page phishing detection”, Mendeley Data, V3, doi: 10.17632/c2gw7fy2j4.3

Thank you Abdelhakim Hannousse for your help.

---

Dataset

• Mendeley Data: Web page phishing detection
• Kaggle: Dataset

---

Installation

• Install python3.10.4
• Create environment

python3 -m venv phishing
source phishing/bin/activate

• Install packages

pip install -r requirements_full.txt

For heroku, use requirements.txt

---

Run

• Check infer.py

cd scripts
python infer.py

• Streamlit app

streamlit run app.py

---

Machine Learning

• main.ipynb contains machine learning model generation and analysis code

---

Feature extraction

Feature extractor code is available here, however some files are missing which included in this repository.

In order to run Feature extractor, some part of the code is commented and modified compare to the original work by author of the paper.