MinerJAB: CLI-based Tool for Detection and Mitigation of Host-Based Cryptojacking Malware

The rise in demand for cryptocurrencies has led to a parallel spike in illegal mining operations that produce digital cash. Since cryptocurrency mining requires huge resources in terms of computing power, adversaries use surreptitious methods to stealthily mine cryptocurrency on the device of the victim unsolicited. In this paper, we propose an automated CLI-based tool MinerJAB, a novel method for detecting host-based cryptojacking malware that blends behavior-based dynamic analysis with host-based detection based on five key cryptomining features. In this study, we investigate three distinct approaches such as the sequential analysis approach, random forest classification, and neural networks in the detection of cryptojacking malware incorporated into MinerJAB. The proposed design is modeled and tested using the same malware dataset and features and compared with the traditional standalone detection mechanisms, and the results are encouraging.