Improving Digital Forensics Through Data Mining
Chrysoula Tsochataridou, Avi Arampatzis, Vasilios Katos · 2014
Abstract — In this paper we reflect upon the challenges a forensic analyst faces when dealing with a complex investigation and develop an approach for handling and analyzing large amounts of data. As traditional digital forensic analysis tools fail to identify hidden relationships in complex modus operandi of perpetrators, in this paper we employ data mining techniques in the digital forensics domain. We consider as a vehicle the Enron scandal, which is recognized to be the biggest audit failure in the U.S. corporate history. In particular, we focus on the textual analysis of the electronic messages sent by Enron employees, using clustering techniques. Our goal is to produce a methodology that could be applied by other researchers, who work on projects that involve email analysis. Preliminary findings show that it is possible to use clustering techniques in order to effectively identify malicious collaborative activities.