On Detecting Cryptojacking on Websites: Revisiting the Use of Classifiers

Abstract

Cryptojacking or illegal mining is a form of malware that hides in the victim’s computer and takes the computational resources to extract cryptocurrencies in favor of the attacker. It generates significant computational consumption, reducing the computational efficiency of the victim’s computer. This attack has increased due to the rise of cryptocurrencies and their profitability and its difficult detection by the user. The identification and blocking of this type of malware have become an aspect of research related to cryptocurrencies and blockchain technology; in the literature, some machine learning and deep learning techniques are presented, but they are still susceptible to improvement. In this work, we explore multiple Machine Learning classification models for detecting cryptojacking on websites, such as Logistic Regression, Decision Tree, Random Forest, Gradient Boosting Classifier, k-Nearest Neighbor, and XGBoost. To this end, we make use of a dataset, composed of network and host features’ samples, to which we apply various feature selection methods such as those based on statistical methods, e.g., Test Anova, and other methods as Wrappers, not only to reduce the complexity of the built models but also to discover the features with the greatest predictive power. Our results suggest that simple models such as Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and k-Nearest Neighbor models, can achieve success rate similar to or greater than that of advanced algorithms such as XGBoost and even those of other works based on Deep Learning.

Прогнозирование Мошеннических Транзакций С Криптовалютой С Использованием Логистической Регрессии

“…It allows you to predict the probability of an object belonging to a certain class and, therefore, can be used to detect fraudulent transactions. The model's high accuracy of 98 percent indicates that it is highly effective, similar to other studies (Mohammed, 2022;Aponte-Novoa, 2022) that used logistic regression on their data. This means that the model can be used in real-world settings to detect fraudulent transactions with high accuracy, which is an important result in the fight against cyber threats and financial crime.…”

Investigating and mitigating blockchain poisoning attacks

“…Double spend threats:An attacker has the ability to pay a merchant, acquire the products or services, and then transfer the remaining funds to an account that is either his own or that of another merchant [2]. Since the account message and the original message conflict with each other, if the secondary consumption message, rather than the original message, is confirmed by the consensus system, the buyer will withdraw the payment, but the merchant will not receive payment for its goods [3].…”

Continuous and Secure Integration Framework for Smart Contracts

“…In addition to the security risks posed against distributed ledgers, such as 51% attack [ 54 ] against blockchain based on mining [ 55 , 56 ], as well as emerging threats as cryptojacking [ 57 ], there are other risks directly against smart contracts. The distributed and immutable characteristics of a smart contract in a blockchain had consequences when faults in them caused economic impacts in multiple cases [ 45 , 58 ].…”