Deanonymizing Bitcoin Transactions via Network Traffic Analysis with Semi-supervised Learning

2026-03-17

AI Summary

Although Bitcoin transactions offer pseudonymity, they remain vulnerable to network-layer de-anonymization attacks, and existing approaches suffer from limited accuracy. This work proposes NTSSL and its enhanced variant NTSSL+, the first methods to integrate semi-supervised learning with cross-layer collaborative analysis for Bitcoin de-anonymization. By leveraging unsupervised algorithms to generate pseudo-labels, the approach substantially reduces annotation costs while jointly reasoning over network traffic features and transaction clustering results. Experimental evaluation demonstrates that the proposed method achieves a 1.6× improvement in de-anonymization accuracy compared to current machine learning-based techniques, significantly enhancing identification performance.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

Privacy protection mechanisms are a fundamental aspect of security in cryptocurrency systems, particularly in decentralized networks such as Bitcoin. Although Bitcoin addresses are not directly associated with real-world identities, this does not fully guarantee user privacy. Various deanonymization solutions have been proposed, with network layer deanonymization attacks being especially prominent. However, existing approaches often exhibit limitations such as low precision. In this paper, we propose \textit{NTSSL}, a novel and efficient transaction deanonymization method that integrates network traffic analysis with semi-supervised learning. We use unsupervised learning algorithms to generate pseudo-labels to achieve comparable performance with lower costs. Then, we introduce \textit{NTSSL+}, a cross-layer collaborative analysis integrating transaction clustering results to further improve accuracy. Experimental results demonstrate a substantial performance improvement, 1.6 times better than the existing approach using machining learning.

Problem

• Bitcoin
• Deanonymization
• Network Traffic Analysis
• Privacy
• Semi-supervised Learning

Innovation

• semi-supervised learning
• network traffic analysis
• transaction deanonymization
• pseudo-labeling
• cross-layer analysis