In this chapter, we were introduced to the detection of the different types of abnormalities in URLs, including URL blacklisting. We also learned about how to use heuristics to detect malicious pages, including using the data for the analysis and extraction of different features. This chapter also taught us how machine learning and logistic regression is used to detect malicious URLs. 

We also learned about using multiclass classification, along with SVM, to detect malicious URLs. In the next chapter, we will learn about the different types of CAPTCHAs.