Existing Datasets & Data Sources

Many datasets exist which are appropraite for information security. These can be used to train and test various machine learning projects which utilise network data to perform analysis. For example intrusion detection systems (IDS), attack prediction and others.

A later section of the course, Open Datasets and Analysis, will contain more detailed informaiton about individual datasets, describing their limitations and other pertinent informaiton.

Download Available


A reference book outlining 11 datasets suitable for security projects is availalbe for Patreon supporters. The current version is v1.0. As with all security kiwi content, reference books are expanded over time.

Collecting Data
Challenges of Datasets