An Attention-based Long Short-Term Memory Framework for Detection of Bitcoin Scams

TL;DR

This paper introduces an attention-based LSTM model for classifying Bitcoin transactions to detect scams, especially Ponzi schemes, demonstrating superior accuracy over existing methods.

Contribution

The paper presents a novel A-LSTM framework specifically designed for Bitcoin scam detection, outperforming traditional classifiers in accuracy and efficiency.

Findings

A-LSTM achieves over 82% F1-score on scam detection data.

The model outperforms Random Forest, Extra Trees, Gradient Boosting, and classical LSTM.

Effective identification of scam-related features in Bitcoin transactions.

Abstract

Bitcoin is the most common cryptocurrency involved in cyber scams. Cybercriminals often utilize pseudonymity and privacy protection mechanism associated with Bitcoin transactions to make their scams virtually untraceable. The Ponzi scheme has attracted particularly significant attention among Bitcoin fraudulent activities. This paper considers a multi-class classification problem to determine whether a transaction is involved in Ponzi schemes or other cyber scams, or is a non-scam transaction. We design a specifically designed crawler to collect data and propose a novel Attention-based Long Short-Term Memory (A-LSTM) method for the classification problem. The experimental results show that the proposed model has better efficiency and accuracy than existing approaches, including Random Forest, Extra Trees, Gradient Boosting, and classical LSTM. With correctly identified scam features, our proposed A-LSTM achieves an F1-score over 82% for the original data and outperforms the existing approaches.