Authors : Kirat Jadhav

Volume/Issue : Volume 5 - 2020, Issue 9 - September

Google Scholar : http://bitly.ws/9nMw

Scribd : https://bit.ly/3iGnYfV

DOI : 10.38124/IJISRT20SEP784

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Cryptocurrencies have revolutionized the process of trading in the digital world. Roughly one decade since the induction of the first bitcoin block, thousands of cryptocurrencies have been introduced. The anonymity offered by the cryptocurrencies also attracted the perpetuators of cybercrime. This paper attempts to examine the different machine learning approaches for efficiently identifying ransomware payments made to the operators using bitcoin transactions. Machine learning models may be developed based on patterns differentiating such cybercrime operations from normal bitcoin transactions in order to identify and report attacks. The machine learning approaches are evaluated on bitcoin ransomware dataset. Experimental results show that Gradient Boosting and XGBoost algorithms achieved better detection rate with respect to precision, recall and F-measure rates when compared with k-Nearest Neighbor, Random Forest, Naïve Bayes and Multilayer Perceptron approaches

Keywords : Blockchain, Bitcoin, Cybercrime, Machine Learning, Ransomware.