Detecting Phishing in Ethereum Networks using Quantum Machine Learning

2026-07-14

AI Summary

This work addresses the limitations of conventional statistical methods and existing quantum machine learning approaches in detecting phishing attacks on the Ethereum network by proposing a hybrid quantum-classical ensemble framework. The framework integrates a Quantum Support Vector Machine (QSVM) with a Variational Quantum Classifier (VQC) and incorporates cascaded Quantum Random Access Coding (QRAC) to enhance data encoding efficiency. Experimental validation was conducted on IBM Heron processors using ZZ feature maps. Results demonstrate that QRAC improves the performance of VQC and QSVM by 13% and 3%, respectively, compared to standard ZZ encoding. The ensemble framework substantially reduces the false negative rate, with QSVM achieving the best performance and approaching simulator-level accuracy on hardware with high quantum volume.

Abstract

This article explores the potential of Quantum Machine Learning (QML), specifically assessing a Quantum Support Vector Machine (QSVM) and a Variational Quantum Classifier (VQC) for detecting anomalies in real-world financial transaction data. While these QML methods outperform statistical methods, they fall short of cutting-edge deep learning techniques. To bridge this gap, we propose a hybrid quantum-classical ensemble framework that leverages the strengths of both domains. We demonstrate its effectiveness in detecting phishing in Ethereum transaction networks by combining complementary algorithms. The QSVM, whether used individually or in an ensemble, consistently delivered the lowest false negatives and higher recall rates, that are crucial for anomaly detection. To enhance individual models, we encoded the data using novel cascaded Quantum Random Access Coding (QRAC) schemes and compared it with the popular encoding ZZ feature map on both simulators and the IBM Heron quantum processor. For both QSVM and VQC, we consistently observed improvements (13% for QRAC-VQC and 3% for QRAC-QSVM) of QRAC over the ZZ feature map. Notably, certain QML algorithms exhibit remarkable resilience on the IBM Heron quantum processor, approaching simulator-level performance on devices with high quantum volume. This observation underscores the promise of QML despite hardware limitations.

Problem

• Phishing Detection
• Ethereum Networks
• Quantum Machine Learning
• Anomaly Detection
• Financial Transactions

Innovation

• Quantum Machine Learning
• Hybrid Quantum-Classical Ensemble
• Cascaded QRAC Encoding
• Phishing Detection
• Ethereum Transaction Networks