De-anonymization of illegal cryptocurrency transactions

Computer Engineering

This project explores the challenges of de-anonymizing Bitcoin transactions in the context of the rapidly expanding digital banking and cryptocurrency landscape. Cryptocurrencies, initially designed for privacy, have inadvertently facilitated various illicit activities. This investigation addresses the urgency to tackle these issues through creative de-anonymization methods, incorporating state-of-the-art research in blockchain analysis and forensic techniques. Our literature survey examines key publications, proposing innovative approaches to identify and prevent illegal transactions, utilizing metrics like Mutual Information. In contrast to the limitations of the existing system, our proposed approach introduces a graph neural network, specifically the graph convolutional network, and leverages self-supervised learning to address challenges related to unlabeled data. Finally, this project provides a comprehensive exploration of de-anonymization strategies, offering valuable insights for researchers, practitioners, and policymakers in addressing the complex challenges at the intersection of cryptocurrency and illicit activities. The convergence of cryptocurrency and illicit activities necessitates adaptive approaches, acknowledging evolving tactics employed by malicious actors.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.