Detection of Abnormal Transactions in Blockchain Based on Multi Feature Fusion

doi:10.3969/j.issn.1671-1122.2022.10.004

Abstract

Abstract:

With the development of blockchain technology, virtual currency represented by bitcoin has become an important tool for money laundering, hacker attacks, telecommunications network fraud and other crimes, which poses a serious threat to the personal and property security of citizens, and even threatens the stability of the national financial market. Therefore, the research on abnormal transaction data detection of virtual currency based on blockchain technology is of great significance. Firstly, this paper use the custom sliding window mechanism to extract the characteristics of blockchain transaction data. Secondly, it procesed from three channels to form three feature vectors according to the characteristics of blockchain transaction data. Finally, it spliced these three feature vectors to build a blockchain abnormal transaction data detection model. This paper verified the feasibility and superiority of the model with the data set released by the blockchain intelligence company Elliptic. The precision, recall and F1 values of the model reached 92.96%, 85% and 92.43%. The experimental results show that the feature vector based on multi-feature fusion contains more abundant blockchain transaction information, which can effectively improve the performance of blockchain abnormal transaction detection.

Key words: blockchain, abnormal transaction detection, sliding window mechanism, multi-feature fusion

CLC Number:

TP309

LIN Wei. Detection of Abnormal Transactions in Blockchain Based on Multi Feature Fusion[J]. Netinfo Security, 2022, 22(10): 24-30.

Figures/Tables 11

References 15

[1]	SONG Qinghua, LI Bohua, LYU Taiheng. The Development of Digital Money and the Construction of Modern Central Bank System[J]. Journal of Regional Financial Research, 2022(1): 5-18.
	宋清华, 李博华, 吕泰亨. 数字货币发展与现代中央银行制度建设[J]. 区域金融研究, 2022(1): 5-18.
[2]	JULLUM M, LOLAND A, HUSEBY R B, et al. Detecting Money Laundering Transactions with Machine Learning[J]. Journal of Money Laundering Control, 2020, 23(1): 173-186.
[3]	CHEN Binjie, WEI Fushan, GU Chunxiang. Blockchain Abnormal Transaction Detection with Privacy-Preserving Based on KNN[J]. Netinfo Security, 2022, 22(3): 78-84.
	陈彬杰, 魏福山, 顾纯祥. 基于KNN的具有隐私保护功能的区块链异常交易检测[J]. 信息网络安全, 2022, 22(3):78-84.
[4]	ZHU Huijuan, CHEN Jinfu, LI Zhiyuan, et al. Block-Chain Abnormal Transaction Detection Method Based on Adaptive Multi-Feature Fusion[J]. Journal on Communications, 2021, 42(5): 41-50.
	朱会娟, 陈锦富, 李致远, 等. 基于多特征自适应融合的区块链异常交易检测方法[J]. 通信学报, 2021, 42(5): 41-50.
[5]	LI Yang, CAI Yue, TIAN Hao, et al. Identifying Illicit Addresses in Bitcoin Network[C]// Springer. International Conference on Blockchain and Trustworthy Systems. Heidelberg: Springer, 2020: 99-111.
[6]	ZHENG Haixiao, WEN Bin. Bitcoin Illegal Transaction Identification Method Based on Graph Convolutional Network[J]. Netinfo Seurity, 2021, 21(9): 74-79.
	郑海潇, 文斌. 基于图卷积网络的比特币非法交易识别方法[J]. 信息网络安全, 2021, 21(9):74-79.
[7]	WEBER M, DOMENICONI G, CHEN Jie, et al. Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics[EB/OL]. [2022-06-15]. https://arxiv.org/abs/1908.02591.
[8]	ANSARI A H, CHANDOK S, IONESCU C. Fixed Point Theorems on B-Metric Spaces for Weak Contractions with Auxiliary Functions[J]. Journal of Inequalities and Applications, 2014(1): 1-17.
[9]	YANG Xingrui, ZHAO Shouwei, ZHANG Ruxue, et al. BiLSTM_CNN Classification Model Based on Self-Attention and Residual Network[J]. Computer Engineering and Applications, 2022, 58(3): 172-180.
	杨兴锐, 赵寿为, 张如学, 等. 结合自注意力和残差的BiLSTM_CNN文本分类模型[J]. 计算机工程与应用, 2022, 58(3): 172-180.
[10]	LI Jinhong. Natural Language Processing Practice Based on BERT Model[M]. Beijing: Publishing House of Electrounics Industry, 2021.
	李金洪. 基于BERT模型的自然语文处理实战[M]. 北京: 电子工业出版社, 2021.
[11]	CHENG Jing, WANG Wei, SHUAI Zhengyi. Intelligent Recommendation Algorithm of Mobile Application Crowdsourcing Test Based on Deep Learning[J]. Journal of Northwestern Polytechnical University, 2021, 39(5): 1049-1056.
	成静, 王威, 帅正义. 基于深度学习的移动应用众包测试智能推荐算法[J]. 西北工业大学学报, 2021, 39(5):1049-1056.
[12]	CHUANG J, GULCEHRE C, CHO K H, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[EB/OL]. [2022-06-15]. https://arxiv.org/abs/1412.3555.
[13]	ZHAO Dandan, HUANG Degen, MENG Jiana, et al. Chinese Entity Relations Classification Based on BERT-GRU-ATT[J]. Computer Science, 2022, 49(6): 319-325.
	赵丹丹, 黄德根, 孟佳娜, 等. 基于BERT-GRU-ATT模型的中文实体关系分类[J]. 计算机科学, 2022, 49(6): 319-325.
[14]	HE Xiaowei, XU Jingjie, WANG Bin, et al. Research on Cloud Computing Resource Load Forecasting Based on GRULSTM Combination Model[J]. Computer Engineering, 2022, 48(5): 11-17, 34.
	贺小伟, 徐靖杰, 王宾, 等. 基于GRU-LSTM组合模型的云计算资源负载预测研究[J]. 计算机工程, 2022, 48(5): 11-17,34.
[15]	ZHAO Yongbin, CHEN Miao, LI Tao, et al. Research on Blockchain Abnormal Transaction Detection Based on Parallel Random Forest[J]. Journal of the Hebei Academy of Sciences, 2021, 38(5): 1-8.
	赵永斌, 陈苗, 李涛, 等. 基于并行的区块链异常交易检测随机森林模型研究[J]. 河北省科学院学报, 2021, 38(5): 1-8.

实验环境	环境配置
CPU	Intel(R) Core(TM) i7-12700KF
GPU	GeForce RTX 3080 Ti
内存	32 GB
操作系统	Window 10操作系统
开发语言	Python 3.9.7
深度学习框架	PyTorch1.10.2

区块链交易集	类别	样本数
Elliptic数据集	合法	42019
	非法	4545
	未知	157509

模型	Precision	Recall	F1
KNN	74.52%	83.24%	78.24%
SVM	53.86%	59.28%	55.75%
决策树	84.71%	83.82%	84.26%
Adaboost模型	62.13%	76.17%	67.19%
MP-GCN^[6]	87.5%	61.2%	70.4%
DNN	92.16%	57.76%	88.8%
LSTM	92.52%	84.25%	91.94%
BiLSTM	92.56%	84.19%	92.07%
GRU	91.77%	82.28%	91.22%
BiGRU	92.06%	82.10%	91.62%
MFF	92.96%	85.00%	92.43%