Train dataset only contains benign traffic, this dataset has been collected using Netflow and implementing a sampling rate of 1 packet out of each 1000 to generate the flows, simulating the conditions of the RedCayle’s routers. The traffic has been generated using three Python scripts. The first one simulates email sending using SMTP protocol. The second script simulates SSH connections. The third script simulates a user browsing the internet using different search engines and different protocols like HTTP and HTTPS.
