Bitcoin Illegal Transaction Identification Method Based on Graph Convolutional Network

doi:10.3969/j.issn.1671-1122.2021.09.011

Abstract

Abstract:

Bitcoin as an anonymous encrypted digital asset has gradually become the choice of some illegal underground transactions. To purify the financial market and combat illegal transactions, it is necessary to identify illegal transaction activities in the Bitcoin network. Based on related work, this article proposed a method for detecting illegal transactions in the Bitcoin network (Multi-layer Perceptrons + Graph Convolutional Network, MP-GCN) based on the combination of a multilayer perceptron and a graph convolutional network. MP-GCN used a combination of multi-layer perceptrons and graph convolutional networks to build a model for identifying illegal transactions. Specifically, before the graph convolutional layer and in the middle of the two-layer graph convolutional layer, a multi-layer perceptron was used for auxiliary feature extraction, and a linear layer was used to divide illegal transactions finally. The experimental results verify that the detection effect achieved by MP-GCN is better than that of the traditional graph convolutional network with the same data set.

Key words: bitcoin network, illegal transaction identification, graph convolutional network

CLC Number:

TP309

ZHENG Haixiao, WEN Bin. Bitcoin Illegal Transaction Identification Method Based on Graph Convolutional Network[J]. Netinfo Security, 2021, 21(9): 74-79.

Figures/Tables 6

References 16

[1]	NAKAMOTO S. Bitcoin: A Peer-to-peer Electronic Cash System[EB/OL]. https://nakamotoinstitute.org/bitcoin/, 2008-10-31.
[2]	BISTARELLI S, SANTINI F. Go with the-bitcoin-flow, with Visual Analytics [C]//ACM. Proceedings of the 12th International Conference on Availability, Reliability and Security, August 29-September 1, 2017, Calabria, ITALY. New York: ACM, 2017: 1-6.
[3]	DECKER C, WATTENHOFER R. Information Propagation in the Bitcoin Network [C]// IEEE. IEEE P2P 2013 Proceedings, September 9-11, 2013, Trento, Italy. Piscataway: IEEE, 2013: 1-10.
[4]	HARLEV M A, SUN Yinhaohua, LANGENHELDT K C, et al. Breaking Bad: De-anonymising Entity Types on the Bitcoin Blockchain Using Supervised Machine Learning [C]//IEEE. Proceedings of the 51st Hawaii International Conference on System Sciences, January 2-6, 2018, Koloa, Hawaii. Piscataway: IEEE, 2018: 3497-3506.
[5]	MONAMO P, MARIVATE V, TWALA B. Unsupervised Learning for Robust Bitcoin Fraud Detection [C]//IEEE. 2016 Information Security for South Africa (ISSA), August 17-18, 2016, Johannesburg, SOUTH AFRICA. New York: IEEE, 2016: 129-134.
[6]	WEBER M, DOMENICONI G, CHEN Jie, et al. Anti-money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics[EB/OL]. https://arxiv.org/abs/1908.02591, 2019-07-31.
[7]	ALARAB I, PRAKOONWIT S, NACER M I. Comparative Analysis Using Supervised Learning Methods for Anti-money Laundering in Bitcoin [C]//ACM. Proceedings of the 2020 5th International Conference on Machine Learning Technologies, June 19-21, 2020, Beijing, China. New York: ACM, 2020: 11-17.
[8]	PHAM T, LEE S. Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods[EB/OL]. https://arxiv.org/abs/1611.03941, 2016-11-12.
[9]	LORENZ J, SILVA M I, APARICIO D, et al. Machine Learning Methods to Detect Money Laundering in The Bitcoin Blockchain in The Presence of Label Scarcity[EB/OL]. https://arxiv.org/abs/2005.14635, 2020-05-29.
[10]	LI Yang, CAI Yue, TIAN Hao, et al. Identifying Illicit Addresses in Bitcoin Network [C]//Springer. International Conference on Blockchain and Trustworthy Systems, August 6-7, 2020, Dali, China. Singapore: Springer, 2020: 99-111.
[11]	ALARAB I, PRAKOONWIT S, NACER M I. Competence of graph Convolutional Networks for Anti-Money Laundering in Bitcoin Blockchain [C]//ACM. Proceedings of the 2020 5th International Conference on Machine Learning Technologies, June 19-21, 2020, Beijing, China. New York: ACM, 2020: 23-27.
[12]	ZHANG Chi, GUO Yuan, LI Ming. Review of Development and Application of Artificial Neural Network Models[J]. Computer Engineering and Applications, 2021, 57(11): 57-69.
	张驰, 郭媛, 黎明. 人工神经网络模型发展及应用综述[J]. 计算机工程与应用, 2021, 57(11): 57-69.
[13]	KIPF T N, WELLING M. Semi-supervised Classification with Graph Convolutional Networks[EB/OL]. http://arxiv.org/abs/1609.02907, 2016-09-09.
[14]	DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering [C]//ACM. Proceedings of the 30th International Conference on Neural Information Processing Systems, December 5-10, 2016, Barcelona, Spain. Red Hook: Curran Associates, 2016: 3844-3852.
[15]	BUSCH J, KOCHETUROV A, TRESP V, et al. NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification [C]//ACM. 33rd International Conference on Scientific and Statistical Database Management, July 6-7, 2021, FL, Tampa, USA. New York: ACM, 2021: 121-132.
[16]	FEY M, LENSSEN J E. Fast Graph Representation Learning with PyTorch Geometric[EB/OL]. https://arxiv.org/abs/1903.02428, 2019-03-06.