A Review on Data Driven Models for Identifying Cryptojacking Malwares

A Review on Data Driven Models for Identifying Cryptojacking Malwares

Rajesh Chouhan1, Prof. Sanmati Jain2

VITM, Indore, India.1,2

ABSTRACT: With the rise of popularity of cryptocurrencies such as Bitcoin, Libra, Ripple, Ethereum etc, more attacks on crypto-currencies have been seen. Crypto-jacking is the unauthorized use of someone else’s computer to mine cryptocurrency. Hackers do this by either getting the victim to click on a malicious link in an email that loads crypto-mining code on the computer, or by infecting a website or online ad with JavaScript code that auto-executes once loaded in the victim’s browser. Apart from the crypto-jackers, web-crypto-mining library providers also enabled benign publishers to use this mechanism as an alternative monetization scheme for extracting revenue.  The cryptojacking attacks have risen significantly with respect to conventional malwares and phishing attacks due to the relatively low risk and high reward nature of cryptojacking attacks. The nature of the attack also makes it extremely complex to detect such attacks. Hence, machine learning based techniques have been at the forefront of detecting cryptojacking. This paper presents the related work in the domain with its salient points and also lays down a methodology for the implementation of a proposed approach for detection of possible cryptojacking attacks.

Keywords: Data-mining, Darkweb, Crypto Mining Crypto currency: Bitcoin; Crypto-jacking; Machine Learning