Fraud Detection in Ethereum Transactions Using Bi-Directional LSTM and Attention Mechanism

Abstract

The decentralized nature of Ethereum exposes it to phishing, Ponzi schemes, and money laundering. Traditional fraud detection methods fail to identify complex patterns in transactions. This paper proposes a deep learning model based on Bi-Directional Long Short-Term Memory (Bi-LSTM) and Attention Mechanism for enhancing fraud detection accuracy in Ethereum transactions. The model handles sequential transaction data and employs Bi-LSTM to learn temporal correlations and Attention to select appropriate features. On a Kaggle Ethereum dataset, the model achieved 97% accuracy, 97% precision, 97% recall, and a 97% F1-score, much higher than existing works. The study demonstrates the usefulness of deep learning for the security of blockchain systems, having a robust process for realtime fraud detection.