Malicious Webpage detection | Coursera Community
Coursera Header

Malicious Webpage detection

  • 8 January 2019
  • 1 reply

Userlevel 3
Badge +4
I want to develop a machine learning model that can classify a webpage as malicious (phishing) or benign based on static features of a url . These features include lexical features, domain features, content based features ( html and JavaScript) . Svm , decision regression tree and neural networks are the mostly used algorithms in research papers .
My opinion is using neural networks. As the dataset is quite large it should work well . Also online learning algorithm can be used with neural network making it adaptive to future changes . What is your opinion on the model? Any other suggestions in methodology or features are welcome.
Note: I am not an expert in machine learning.
I have completed a course in machine learning and a deeplearning specialization from coursera.
Thanks in advance.

1 reply

Userlevel 5
Badge +5
@THANGA MANICKAM M I think you should try any suitable model to start off, just keep it simple. See if you model works reasonably well. Then you can always compare different algorithms and tune the model more later on.


    Cookie policy

    We use cookies to enhance and personalize your experience. If you accept you agree to our full cookie policy. Learn more about our cookies.

    Accept cookies Cookie settings