Detecting Ransomware in Bitcoin Network: Experimental Insights

Abstract

Ransomware attacks, exploiting cryptocurrencies like Bitcoin for ransom payments, represent a significant cybersecurity threat. Detecting these malicious activities within the Bitcoin network is challenging due to complex transaction patterns and blockchain’s inherent anonymity. Understanding these patterns is crucial for effective defense mechanisms. However, existing research lacks comprehensive analysis of ransomware behavior on the Bitcoin network, leaving gaps in understanding. Moreover, current detection strategies often struggle to accurately identify ransomware activities. To address these gaps, this study conducted experimental research using the BitcoinHeist dataset. Employing machine learning techniques and feature engineering, the analysis aims to decipher transaction patterns and identify ransomware characteristics. The model achieves an accuracy of 85%, demonstrating its effectiveness in detecting ransomware activities. By bridging theoretical knowledge with empirical analysis, this research enhances understanding and aids in developing robust defense strategies against ransomware attacks.