In our previous entry of the Ex Machina series, we gave a broad overview of how machine learning is used in computer security, and briefly mentioned some of the techniques that InQuest is utilizing to apply the insights gained by our artificial co-workers. Today, we’re going to take a deeper dive into two of our classifiers, Random Forests (RF) and Gradient Boosting (GB), and discuss some of their interesting findings. As Gradient Boosting is more a subtype of Random Forest, rather than an entirely separate algorithm in and of itself, we’ll just be given an explanation of RF algorithms; GB forests add a few more high-level mathematical calculations to how they construct and uses their trees.
Here at InQuest, YARA is among the many tools we use to perform deep-file inspection, with a fairly extensive rule set. InQuest operates at line speed in very high-traffic networks, so these rules need to be fast.
This blog post is the second in a series discussing YARA performance notes, tips, and hacks.
Since its introduction by WheelGroup in 1995, signature-based detection has been a staple of antivirus software. Now, over twenty years later, it seems that it’s reached the limits of its usefulness. In 2016, the Webroot Threat Report published that, thanks to a large spike in the usage of polymorphic, or self-altering, code, 94% of malware that year was found to be unique, having only been encountered once. This is a trend that has only been continuing into 2018, and, like shaking an Etch-A-Sketch, with every shift in form taken by a malicious file, all work done on defining its characteristics becomes obsolete. We at InQuest have found a robust solution to this problem via the use of generalized, heuristic signatures that work together to give an overall likelihood of a file’s potential maliciousness, but such signatures can be difficult and unintuitive to create.
After the demise of the Dyreza banking malware, the banking trojan vacuum was quickly filled by the TrickBot malware family. TrickBot is a banking and information stealing trojan which is modular in design and can rapidly expand its functionality by retrieving DLLs from its Command and Control server. This threat is spread most commonly by phishing emails but it also includes network propagation functionality to spread through a victims network by using the Microsoft Windows vulnerability known as EternalRomance. In this blog post, we'll dive into the TrickBot malware, its functionality, modules, and Command and Control communications.