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.

Talking about cyber scams might make AI sound scary, but Murphy said it's important to remember that legitimate organizations use it for positive purposes, too. "AI can be both good and bad," he said. "From a cybersecurity perspective, we're using AI to help us develop tools and techniques to protect our own systems. We find patterns and create defenses that are more predictive and proactive, rather than being reactive." Murphy said many organizations use AI to teach their computers to detect when other computers are trying to penetrate their cybersecurity measures.