Article Details
  • Published Online:
    January  2025
  • Product Name:
    The IUP Journal of Computer Sciences
  • Product Type:
    Article
  • Product Code:
    IJCS010125
  • DOI:
    10.71329/IUPJCS/2025.19.1.7-17
  • Author Name:
    Taiwo O Adigun, Akinola Oshinubi and Ibukun Eweoya
  • Availability:
    YES
  • Subject/Domain:
    Engineering
  • Download Format:
    PDF
  • Pages:
    7-17
Volume 19, Issue 1, January 2025
Cryptojacking Detection Using ML Techniques
Abstract

The study proposes a novel approach to detecting crypto clients by monitoring their network traffic, even when it is encrypted. It focuses on Bitcoin (BTC), Mercato (MERC), and Byte Coin (BYTC) traffic, and other major cryptocurrencies’ (BYTEC) regular and VPN-shaped traffic. The method also involves identification of cryptocurrency-related activities using six different ML algorithms: Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest and k-Nearest Neighbors (KNN). The two detection approaches (Decision Tree and Random Forest) effectively identify cryptocurrency-related activities by analyzing network traffic and also web application vulnerabilities, while others did not give the expected results. The Random Forest detector gave the best result. The study offers a promising solution to the problem of crypto mining malware. The method has been found to be effective in identifying cryptocurrency-related activities and web application vulnerabilities, and can be used to keep operating systems safe.

Introduction

There are many hazards in today’s digital world, but cryptojacking is one of the more persistent ones (Caporale et al., 2018). More malware code authors are now including cryptojacking and crypto mining features in their programs, which is a new shift in the realm of cybercrime.