Shedding Light on Log Correlation in Network Forensics Analysis

Abstract

Presently, forensics analyses of security incidents rely largely on manual, ad-hoc, and very time-consuming processes. A security analyst needs to manually correlate evidence from diverse security logs with expertise on suspected malware and background on the configuration of an infrastructure to diagnose if, when, and how an incident happened. To improve our understanding of forensics analysis processes, in this work we analyze the diagnosis of 200 infections detected within a large operational network. Based on the analyzed incidents, we build a decision support tool that shows how to correlate evidence from different sources of security data to expedite manual forensics analysis of compromised systems. Our tool is based on the C4.5 decision tree classifier and shows how to combine four commonly-used data sources, namely IDS alerts, reconnaissance and vulnerability reports, blacklists, and a search engine, to verify different types of malware, like Torpig, SbBot, and FakeAV. Our evaluation confirms that the derived decision tree helps to accurately diagnose infections, while it exhibits comparable performance with a more sophisticated SVM classifier, which however is much less interpretable for non statisticians.