Detecting Malicious Traffic with Machine Learning

Verizon Media Platform
Aug 29 · 9 min read
Figure 1. We generate various groups with different behavior such as Inter-request time and the total number of unique endpoints (or URLs). Data points in each group exhibit similar behavior.
Figure 2. When we test a model, we apply the classifier to a new set of data. We want to answer the following questions: Did our model discover new clients that exhibit known bad behavior? Does our model detect requests by bots or valid users (humans)?

Verizon Media Platform

Written by

Deliver the premium experiences your consumers demand with an industry-leading platform renowned for its performance, reliability, security, and scale: http://

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade