This app shows how to Operationalize Machine Learning using MLTK to detect malicious domain names. Malware like botnets use domain generation algorithms (DGAs) to create URLs that host malicious websites or command and control servers. Static matching does not always help, so machine learning models can add value and allow to increase detection rates.
For details about how this app works in detail please look for upcoming informations in the next app update and checkout the whitepaper available: https://www.splunk.com/en_us/form/operationalizing-machine-learning-to-detect-malicious-domain.html
Prerequesites for this app:
Go check the setup dashboard for more detailed setup steps.
Third party references:
The datasets that ship with the app are composed of 2 sources:
1. DGA domain names were generated with scripts from Johannes Bader DGA reversing scripts available from https://github.com/baderj/domain_generation_algorithms
2. Legit domain names were taken from Cisco Umbrella 1 Million from https://umbrella.cisco.com/blog/2016/12/14/cisco-umbrella-1-million/
Checked compatibility with Splunk 8.0 and MLTK 5.0.
Minor fixes on Dashboard 4 (select SVM model) and KVStore results cutoff.
Vetted for Splunk Cloud (still needs manual install, please work with cloud ops), minor fixes
As a Splunkbase app developer, you will have access to all Splunk development resources and receive a 10GB license to build an app that will help solve use cases for customers all over the world. Splunkbase has 1000+ apps from Splunk, our partners and our community. Find an app for most any data source and user need, or simply create your own with help from our developer portal.