Tools and Technologies Used:

​

I will use the "ISCX-URL-2016 dataset" by Canadian Institute for Cyber Security. The dataset contains five classes of Malicious URLs(Benign, Spam, Phishing, Malware & Defacement) and is collected from various authorized sources dedicated to filtering URLs.

​

Python 3.0 and its following libraries useful for Data Science.

 

• Pandas for handling complex data structures

• Numpy for data matrix operations

• Seaborn/Matplotlib for visualization of data

• Scikit Learn for Machine Learning Process (ML Model Training and Validation)

​

IDE: Visual Studio Code or Jupyter Notebook