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

Abstract

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

CLC Number:

TP18

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.

Figures/Tables 12

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

References 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.

Metrics

Recommended 0

No Suggested Reading articles found!

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%

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

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 33

Related Articles 6

Metrics

Recommended 0

[1]	Jiang’an DAI, Shengyang LUAN, Minglong ZHAO, Zhaojun ZHANG, Tianshuang QIU. Pol-CCES based modulation recognition method under impulsive noise [J]. Journal on Communications, 2021, 42(12): 121-133.
[2]	Ying WANG, Jun REN, Ke SHI, Bin LIN. Doubly-selective channel estimation for generalized frequency division multiplexing systems based on deep learning [J]. Journal on Communications, 2021, 42(10): 233-242.
[3]	Jingyi QU,Meng YE,Xing QU. Airport delay prediction model based on regional residual and LSTM network [J]. Journal on Communications, 2019, 40(4): 149-159.
[4]	Huilan LUO, Kang TONG. Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition [J]. Journal on Communications, 2019, 40(10): 189-198.
[5]	Jia LI,Xiaochun YUN,Shuhao LI,Yongzheng ZHANG,Jiang XIE,Fang FANG. HTTP malicious traffic detection method based on hybrid structure deep neural network [J]. Journal on Communications, 2019, 40(1): 24-33.
[6]	Xun-yi REN,Ru-chuan WANG,Hai-yan WANG. Wavelet analysis method for detection of DDoS attack based on self-similar [J]. Journal on Communications, 2006, 27(5): 6-11.