Know Abnormal, Find Evil: Frequent Pattern Mining for Ransomware Threat Hunting and Intelligence

TLDR

Crypto‑ransomware has reshaped the cyber threat landscape by encrypting victims’ data to deny access, making timely detection reliant on rapid, accurate mining of system logs for abnormal activity. The study establishes a logging environment for 517 Locky, 535 Cerber, and 572 TeslaCrypt samples to enable systematic analysis of ransomware behavior. Sequential Pattern Mining identifies maximal frequent activity patterns within each ransomware family, which are then used as features for classification with J48, Random Forest, Bagging, and MLP algorithms. The approach achieves 99 % accuracy distinguishing ransomware from benign software and 96.5 % accuracy classifying ransomware families, demonstrating that distinctive frequent patterns can effectively support threat hunting and intelligence.

Abstract

Emergence of crypto-ransomware has significantly changed the cyber threat landscape. A crypto ransomware removes data custodian access by encrypting valuable data on victims' computers and requests a ransom payment to re-instantiate custodian access by decrypting data. Timely detection of ransomware very much depends on how quickly and accurately system logs can be mined to hunt abnormalities and stop the evil. In this paper we first setup an environment to collect activity logs of 517 Locky ransomware samples, 535 Cerber ransomware samples and 572 samples of TeslaCrypt ransomware. We utilize Sequential Pattern Mining to find Maximal Frequent Patterns (MFP) of activities within different ransomware families as candidate features for classification using J48, Random Forest, Bagging and MLP algorithms. We could achieve 99 percent accuracy in detecting ransomware instances from goodware samples and 96.5 percent accuracy in detecting family of a given ransomware sample. Our results indicate usefulness and practicality of applying pattern mining techniques in detection of good features for ransomware hunting. Moreover, we showed existence of distinctive frequent patterns within different ransomware families which can be used for identification of a ransomware sample family for building intelligence about threat actors and threat profile of a given target.