SAS® Viya® AI for Cybersecurity: Malware Control

[#1]

This presentation illustrated malware detection enhancement using unsupervised and semi-supervised machine learning techniques to detect early zero-day attacks. Malware authors generate domains for command-and-control communication using domain generation algorithms (DGA). Different types of malware employ different algorithms. Our challenge is to classify a given domain as a DGA domain or non-DGA (benign) domain. A device that accesses a DGA domain is potentially infected with malware. Learn how we used SAS Viya to apply multiple advanced analytics techniques.

Presentation slides are attached to this post.

[Evianexxy]

I came across this older discussion and wanted to add that I’m curious whether anyone has tried blending these semi-supervised methods with newer threat‑intel feeds to boost early detection. I’ve seen some teams get good results by enriching DGA-related features with passive DNS data. Has anyone here experimented with that approach or found other signals that pair well with Viya’s models?

[Evianexxy]

I’ve found it pretty handy to lean on their tech side whenever I’m trying to streamline security across projects, and their focus on digital assets fits nicely if you’re juggling both infrastructure and long-term strategy. Since they’re active in places like Dubai and Hong Kong, getting quick feedback has been easy for me through their contact form.