基于多特征自适应融合的区块链异常交易检测方法

doi:10.11959/j.issn.1000-436x.2021030

通信学报 ›› 2021, Vol. 42 ›› Issue (5): 41-50.doi: 10.11959/j.issn.1000-436x.2021030

所属专题：区块链

基于多特征自适应融合的区块链异常交易检测方法

朱会娟¹^,², 陈锦富¹^,², 李致远¹^,², 殷尚男¹^,²

¹ 江苏大学计算机科学与通信工程学院，江苏镇江 212013
² 江苏省工业网络安全技术重点实验室，江苏镇江 212013

修回日期:2020-11-20 出版日期:2021-05-25 发布日期:2021-05-01
作者简介:朱会娟（1984- ），女，河南洛阳人，博士，江苏大学副教授、硕士生导师，主要研究方向为区块链、网络安全及人工智能
陈锦富（1978- ），男，江西信丰人，博士，江苏大学教授、博士生导师，主要研究方向为可信软件及软件安全
李致远（1981- ），男，河南开封人，博士，江苏大学副教授、硕士生导师，主要研究方向为物联网、大数据安全
殷尚男（1989- ），男，吉林白城人，博士，江苏大学副教授，主要研究方向为入侵检测及孤立点检测
基金资助:
国家重点研发计划基金资助项目(2017YFB1400700);江苏省前沿引领技术基础研究专项基金资助项目(BK20202001);国家自然科学基金资助项目(61802154);国家自然科学基金资助项目(61702230);国家自然科学基金资助项目(U1836116)

Block-chain abnormal transaction detection method based on adaptive multi-feature fusion

Huijuan ZHU¹^,², Jinfu CHEN¹^,², Zhiyuan LI¹^,², Shangnan YIN¹^,²

¹ School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China
² Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace, Zhenjiang 212013, China

Revised:2020-11-20 Online:2021-05-25 Published:2021-05-01
Supported by:
The National Key Research and Development Program of China(2017YFB1400700);The Leading-edge Technology Program of Jiangsu Natural Science Foundation(BK20202001);The National Natural Science Foundation of China(61802154);The National Natural Science Foundation of China(61702230);The National Natural Science Foundation of China(U1836116)

摘要/Abstract

摘要：

针对智能检测模型的性能受限于原始数据（特征）表达能力的问题，设计了一种残差网络结构ResNet-32用于挖掘区块链交易特征间隐含的关联关系，自动学习包含丰富语义信息的高层抽象特征。虽然浅层特征区分能力弱，但更忠于原始交易细节的描述，如何充分利用两者的优势是提升异常交易检测性能的关键，因此提出了特征融合方法自适应地桥接高层抽象特征与原始特征之间的鸿沟，自动去除其噪声和冗余信息，并挖掘两者的交叉特征信息获得最具区分力的特征。最后，结合以上方法提出区块链异常交易检测模型（BATDet），并通过Elliptic数据集验证了所提模型在区块链异常交易检测领域的有效性。

关键词: 区块链, 残差网络, 异常检测, Logistic回归

Abstract:

Aiming at the problem that the performance of intelligent detection models was limited by the representation ability of original data (features), a residual network structure ResNet-32 was designed to automatically mine the intricate association relationship between original features, so as to actively learn the high-level abstract features with rich semantic information.Low-level features were more transaction content descriptive, although their distinguishing ability was weaker than that of the high-level features.How to integrate them together to obtain complementary advantages was the key to improve the detection performance.Therefore, multi feature fusion methods were proposed to bridge the gap between the two kinds of features.Moreover, these fusion methods can automatically remove the noise and redundant information from the integrated features and further absorb the cross information, to acquire the most distinctive features.Finally, block-chain abnormal transaction detection model (BATDet) was proposed based on the above presented methods, and its effectiveness in the abnormal transaction detection is verified.

Key words: block-chain, residual network, abnormal detection, Logistic regression

中图分类号:

TP18

朱会娟, 陈锦富, 李致远, 殷尚男. 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.

Huijuan ZHU, Jinfu CHEN, Zhiyuan LI, Shangnan YIN. Block-chain abnormal transaction detection method based on adaptive multi-feature fusion[J]. Journal on Communications, 2021, 42(5): 41-50.

图/表 12

表1

图1

图2

图3

表2

残差网络参数设置"

块名	输出形状	块结构（32层）
Conv₁	166×1	3x1,64,stride 2
Conv₁	166×1	BN 1D（64）,MaxPool,3×1,stride 2
Conv₂	166×1	$[\begin{matrix} 3 \times 1, 64 \\ 3 \times 1, 64 \end{matrix}] \times 3$
Conv₃	83×1	$[\begin{matrix} 3 \times 1, 128 \\ 3 \times 1, 128 \end{matrix}] \times 3$
Conv₄	42×1	$[\begin{matrix} 3 \times 1, 256 \\ 3 \times 1, 256 \end{matrix}] \times 3$
Conv₅	21×1	$[\begin{matrix} 3 \times 1, 312 \\ 3 \times 1, 312 \end{matrix}] \times 3$
Conv₆	11×1	$[\begin{matrix} 3 \times 1, 512 \\ 3 \times 1, 512 \end{matrix}] \times 3$
全连接层	1×1	全局平均池化 512-2 FC, Softmax

表2

表3

图4

图5

图6

图7

图8

表4

参考文献 33

[1]	龚鸣 . 非基于 KYC 的区块链反洗钱技术探讨[J]. 清华金融评论, 2017,4: 52-54.
	GONG M . Discussion on anti money laundering technology of blockchain nor based on KYC[J]. Tsinghua Financial Review, 2017,4: 52-54.
[2]	QI T T , WANG T M , ZHU J M ,et al. Empirical study on the correlation and volatility between bitcoin and the blockchain index:based on granger causality test and GARCH-class model[C]// The 4th International Conference on Crowd Science and Engineering. New York:ACM Press, 2019: 28-32.
[3]	WEBER M , DOMENICONI G , CHEN J ,et al. Anti-money laundering in bitcoin:experimenting with graph convolutional networks for financial forensics[J]. arXiv Preprint,arXiv:1908.02591, 2019.
[4]	钱卫宁, 邵奇峰, 朱燕超 ,等. 区块链与可信数据管理:问题与方法[J]. 软件学报, 2018,29(1): 150-159.
	QIAN W N , SHAO Q F , ZHU Y C ,et al. Research problems and methods in blockchain and trusted data management[J]. Journal of Software, 2018,29(1): 150-159.
[5]	LECUN Y , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015,521(7553): 436-444.
[6]	REN K , ZHENG T H , QIN Z ,et al. Adversarial attacks and defenses in deep learning[J]. Engineering, 2020,6(3): 346-360.
[7]	ZHAO Z Q , ZHENG P , XU S T ,et al. Object detection with deep learning:a review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019,30(11): 3212-3232.
[8]	Elliptic. Elliptic company[R].(2019)[2020-11-20].
[9]	余春堂, 韩志耕, 李致远 ,等. 基于区块链的众包物流分级多层智能服务交易监管架构[J]. 网络与信息安全学报, 2020,6(3): 50-58.
	YU C T , HAN Z G , LI Z Y ,et al. Blockchain-based hierarchical and multi-level smart service transaction supervision framework for crowdsourcing logistics[J]. Chinese Journal of Network and Information Security, 2020,6(3): 50-58.
[10]	JULLUM M , LLAND A , HUSEBY R B ,et al. Detecting money laundering transactions with machine learning[J]. Journal of Money Laundering Control, 2020,23(1): 173-186.
[11]	DEMETIS D S . Fighting money laundering with technology:a case study of Bank X in the UK[J]. Decision Support Systems, 2018,105: 96-107.
[12]	PAULA E L , LADEIRA M , CARVALHO R N ,et al. Deep learning anomaly detection as support fraud investigation in Brazilian exports and anti-money laundering[C]// 2016 15th IEEE International Conference on Machine Learning and Applications. Piscataway:IEEE Press, 2016: 954-960.
[13]	CHEN Z Y , KHOA L D , TEOH E N ,et al. Machine learning techniques for anti-money laundering (AML) solutions in suspicious transaction detection:a review[J]. Knowledge and Information Systems, 2018,57(2): 245-285.
[14]	PHAM T , LEE S . Anomaly detection in the bitcoin system - a network perspective[J]. arXiv Preprint,arXiv:1611.03942v2, 2016.
[15]	LORENZ J , SILVA M L , APARICIO D ,et al. Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity[J]. arXiv Preprint,arXiv:1611.03942v2, 2016.
[16]	李韵, 黄辰林, 王中锋 ,等. 基于机器学习的软件漏洞挖掘方法综述[J]. 软件学报, 2020,31(7): 2040-2061.
	LI Y , HUANG C L , WANG Z F ,et al. Survey of software vulnerability mining methods based on machine learning[J]. Journal of Software, 2020,31(7): 2040-2061.
[17]	LI X , DING M L , PI?URICA A . Deep feature fusion via two-stream convolutional neural network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020,58(4): 2615-2629.
[18]	王勇, 周慧怡, 俸皓 ,等. 基于深度卷积神经网络的网络流量分类方法[J]. 通信学报, 2018,39(1): 14-23.
	WANG Y , ZHOU H Y , FENG H ,et al. Network traffic classification method basing on CNN[J]. Journal on Communications, 2018,39(1): 14-23.
[19]	刘烨, 黄金筱, 马于涛 . 基于混合神经网络和注意力机制的软件缺陷自动分派方法[J]. 计算机研究与发展, 2020,57(3): 461-473.
	LIU Y , HUANG J X , MA Y T . An automatic method using hybrid neural networks and attention mechanism for software bug triaging[J]. Journal of Computer Research and Development, 2020,57(3): 461-473.
[20]	PANG J M , CHEN K , SHI J P ,et al. Libra R-CNN:towards balanced learning for object detection[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2019: 821-830.
[21]	LIU S , HUANG D , WANG Y . Learning spatial fusion for single-shot object detection[J]. arXiv Preprint,arXiv:1911.09516, 2019.
[22]	GHIASI G , LIN T Y , LE Q V . NAS-FPN:learning scalable feature pyramid architecture for object detection[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2019: 7029-7038.
[23]	ZHANG Z , ZHANG X , PENG C ,et al. ExFuse:enhancing feature fusion for semantic segmentation[C]// European Conference on Computer Vision. Berlin:Springer, 2018: 273-288.
[24]	VINCENT P , LAROCHELLE H , LAJOIE I ,et al. Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010,11(12): 3371-3408.
[25]	LI K , ZOU C Q , BU S H ,et al. Multi-modal feature fusion for geographic image annotation[J]. Pattern Recognition, 2018,73: 1-14.
[26]	LI G H , MATTHIAS M , QIAN G C ,et al. DeepGCNs:making GCNs go as deep as CNNs[J]. arXiv Preprint,arXiv:1904.03751, 2019.
[27]	刘树东, 王晓敏, 张艳 . 一种对称残差 CNN 的图像超分辨率重建方法[J]. 西安电子科技大学学报, 2019,46(5): 15-23.
	LIU S D , WANG X M , ZHANG Y . Symmetric residual convolution neural networks for the image super-resolution reconstruction[J]. Journal of Xidian University, 2019,46(5): 15-23.
[28]	HE K M , ZHANG X Y , REN S Q ,et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.
[29]	裴伟, 许晏铭, 朱永英 ,等. 改进的 SSD 航拍目标检测方法[J]. 软件学报, 2019,30(3): 738-758.
	PEI W , XU Y M , ZHU Y Y ,et al. The target detection method of aerial photography images with improved SSD[J]. Journal of Software, 2019,30(3): 738-758.
[30]	NAIR V , HINTON G E . Rectified linear units improve restricted Boltzmann machines Vinod Nair[C]// IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2010: 807-814.
[31]	CHEN Y S , JIANG H L , LI C Y ,et al. Deep feature extraction and classification of hyper spectral images based on convolutional neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016,54(10): 6232-6251.
[32]	IOFFE S , SZEGEDY C . Batch normalization:accelerating deep network training by reducing internal covariate shift[J]. arXiv Preprint,arXiv:1502.03167, 2015.
[33]	KINGMAD , BA J . Adam:a method for stochastic optimization[C]// International Conference on Learning Representations. Piscataway:IEEE Press, 2015: 1-11.

方法	优势	不足
基于规则	①简单、快捷，②适于单一静态场景	①难以应对复杂动态场景，②过度依赖人工参与、缺乏灵活性
无监督学习	①不需要标签，②自动化程度高	①高误报率与高漏报率，②对特征中的噪声敏感
有监督学习	①预测精度高，②适用性广，③结果容易理解	①需要高质量标记样本，②检测性能受限于原始数据（特征）的表达能力

方法	Accuracy	Precision	Recall	F1-score	MCC
Raw	88.70%	32.86%	70.91%	69.31%	43.20%
ResNet-32	97.46%	86.18%	72.58%	88.72%	77.79%
RRCF	97.53%	87.49%	72.30%	88.93%	78.27%
RRSF	97.77%	92.89%	71.20%	89.71%	80.24%
RRUF	97.86%	94.59%	71.10%	90.02%	80.99%

模型	Accuracy	Precision	Recall	F1-score	MCC
KNN	93.66%	50.95%	64.45%	76.74%	53.97%
DT	92.47%	45.28%	76.18%	76.34%	55.12%
MLP	95.13%	63.62%	59.46%	79.31%	58.77%
NB	70.16%	16.33%	87.17%	54.36%	29.07%
Adaboost	96.21%	72.29%	67.68%	83.94%	67.93%
GBDT	97.10%	80.72%	72.67%	87.47%	75.06%
ResNet-32	97.46%	86.18%	72.58%	88.72%	77.79%
RRCF	97.53%	87.49%	72.30%	88.93%	78.27%
RRSF	97.77%	92.89%	71.20%	89.71%	80.24%
RRUF	97.86%	94.59%	71.10%	90.02%	80.99%

基于多特征自适应融合的区块链异常交易检测方法

Block-chain abnormal transaction detection method based on adaptive multi-feature fusion

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 33

相关文章 15

Metrics

推荐阅读 0

[1]	张海波, 曹钰坤, 刘开健, 王汝言. 车联网中基于区块链的分布式信任管理方案[J]. 通信学报, 2023, 44(5): 148-157.
[2]	刘雪娇, 钟强, 夏莹杰. 基于双层分片区块链的车联网跨信任域高效认证方案[J]. 通信学报, 2023, 44(5): 213-223.
[3]	冯涛, 陈李秋, 方君丽, 石建明. 基于本地化差分隐私和属性基可搜索加密的区块链数据共享方案[J]. 通信学报, 2023, 44(5): 224-233.
[4]	夏莹杰, 朱思雨, 刘雪娇. 区块链架构下具有条件隐私的车辆编队跨信任域高效群组认证研究[J]. 通信学报, 2023, 44(4): 111-123.
[5]	蒋丽, 谢胜利, 田辉. 面向数字孪生边缘网络的区块链分片及资源自适应优化机制[J]. 通信学报, 2023, 44(3): 12-23.
[6]	戴千一, 张斌, 郭松, 徐开勇. 基于多分类器集成的区块链网络层异常流量检测方法[J]. 通信学报, 2023, 44(3): 66-80.
[7]	经普杰, 王良民, 董学文, 张玉书, 王骞, Muhammad Sohail. 分层跨链结构：一种面向区块链系统监管的可行架构[J]. 通信学报, 2023, 44(3): 93-104.
[8]	刘雪娇, 曹天聪, 夏莹杰. 区块链架构下高效的车联网跨域数据安全共享研究[J]. 通信学报, 2023, 44(3): 186-197.
[9]	霍纬纲, 梁锐, 李永华. 基于随机Transformer的多维时间序列异常检测模型[J]. 通信学报, 2023, 44(2): 94-103.
[10]	黄冬艳, 李琨. 多地址的时间型区块链隐蔽通信方法研究[J]. 通信学报, 2023, 44(2): 148-159.
[11]	杨亚涛, 刘德莉, 刘培鹤, 曾萍, 肖嵩. BFV-Blockchainvoting：支持BFV全同态加密的区块链电子投票系统[J]. 通信学报, 2022, 43(9): 100-111.
[12]	冯霞, 崔凯平, 谢晴晴, 王良民. VANET中基于区块链的分布式匿名认证方案[J]. 通信学报, 2022, 43(9): 134-147.
[13]	李雷孝, 杜金泽, 林浩, 高昊昱, 杨艳艳, 高静. 区块链网络隐蔽信道研究进展[J]. 通信学报, 2022, 43(9): 209-223.
[14]	熊礼治, 朱蓉, 付章杰. 基于交易构造和转发机制的区块链网络隐蔽通信方法[J]. 通信学报, 2022, 43(8): 176-187.
[15]	杜瑞忠, 张添赫, 石朋亮. 基于区块链且支持数据共享的密文策略隐藏访问控制方案[J]. 通信学报, 2022, 43(6): 168-178.