I'm far from an expert but "these samples cluster around this rule or this
subset of rules" is far from machine learning. There's no learning there at all.
We have used YARA to extract out features from various documents (specifically
things like RTF where you can easily count
Hi Everyone,
I am a college student working on a malware detection project.
Someone told me that "*Yara rules can also be used to convert a big data
set in the form of clusters in machine learning " and it has a different
use at different platforms.*
I am a bit confused,