Introduction to Open Datasets and Analysis

This section aims to provide learners with a library of open datasets useful for cyber security purposes, along with analysis of each describing their strengths and weaknesses. While the analysis cannot be exhausive (due to the number of applications), the analysis will be useful to beginner and intermediate learners looking for appropraite datasets for experimentation and their own projects.

The Database Library

  • UGR’16
  • DARPA 1998/9(coming soon)
  • KDDCup 1999 (coming soon)
  • Sperotto 2009 (coming soon)
  • NSL-KDD 2009 (coming soon)
  • MAWI 2010 (coming soon)
  • More coming

Many more datasets will be added over time.


Convolutional Neural Network
UGR16 Dataset