An Efficient Approach to Detect TorrentLocker Ransomware in Computer Systems

摘要

TorrentLocker is a ransomware that encrypts sensitive data located on infected computer systems. Its creators aim to ransom the victims, if they want to retrieve their data. Unfortunately, antiviruses have difficulties to detect such polymorphic malware. In this paper, we propose a novel approach to detect online suspicious processes accessing a large number of files and encrypting them. Such a behavior corresponds to the classical scenario of a malicious ransomware. We show that the Kullback-Liebler divergence can be used to detect with high effectiveness whether a process transforms structured input files (such as JPEG files) into unstructured encrypted files, or not. We focus mainly on JPEG files since irreplaceable pictures represent in many cases the most valuable data on personal computers or smartphones.