基于KNN的具有隐私保护功能的区块链异常交易检测

doi:10.3969/j.issn.1671-1122.2022.03.009

信息网络安全 ›› 2022, Vol. 22 ›› Issue (3): 78-84.doi: 10.3969/j.issn.1671-1122.2022.03.009

基于KNN的具有隐私保护功能的区块链异常交易检测

陈彬杰¹, 魏福山¹^,², 顾纯祥¹^,²()

1. 信息工程大学网络空间安全学院,郑州450001
2. 河南省网络密码技术重点实验室,郑州 450001

收稿日期:2021-04-15 出版日期:2022-03-10 发布日期:2022-03-28
通讯作者: 顾纯祥 E-mail:gcx5209@126.com
作者简介:陈彬杰（1996—）,男,河南,硕士研究生,主要研究方向为区块链异常交易检测|魏福山（1983—）,男,甘肃,副教授,博士,主要研究方向为密码学|顾纯祥（1976—）,男,安徽,教授,博士,主要研究方向为密码学
基金资助:
国家自然科学基金(61772548)

Blockchain Abnormal Transaction Detection with Privacy-preserving Based on KNN

CHEN Binjie¹, WEI Fushan¹^,², GU Chunxiang¹^,²()

1. School of Cyberspace Security, Information Engineering University, Zhengzhou 450001, China
2. Henan Key Laboratory of Network Cryptography Technology, Zhengzhou 450001, China

Received:2021-04-15 Online:2022-03-10 Published:2022-03-28
Contact: GU Chunxiang E-mail:gcx5209@126.com

摘要/Abstract

摘要：

随着区块链技术的发展,以Hyperledger为代表的联盟链技术得到了广泛应用,其异常交易检测需求也逐渐凸显。但当前的区块链异常交易检测技术大多针对公有链设计,没有考虑联盟链交易的隐私保护需求。为了实现高效异常检测并保证联盟链交易的隐私性,文章提出一种基于KNN的具有隐私保护功能的区块链异常交易检测方案。该方案中记账节点使用矩阵乘法对交易数据进行随机化,云服务器使用KNN对随机化后的交易数据特征进行异常检测,并将结果反馈给联盟链记账节点进行验证。实验结果表明,该方案对联盟链效率的影响很小,同时具有良好的检测效果,召回率、精度、F1值分别可达85.3%、87.7%和86.5%。

关键词: 区块链, 联盟链, 异常检测, 隐私保护, KNN

Abstract:

With the development of blockchain, the consortium blockchain technology represented by Hyperledger has been applied widely, and its abnormal transaction detection needs have become prominent gradually. The current anomaly detection technology focuses on public blockchain, which neglects the privacy protection requirements of the consortium blockchain. In order to realize efficient anomaly detection and privacy protection of the consortium blockchain, this paper proposed a privacy-preserving abnormal transaction detection scheme based on KNN. The accounting nodes of this scheme used the matrix method to randomize the transaction data, and cloud server used KNN to test the randomized transaction data and feed back the result to accounting nodes for validation. The experimental results show that the scheme has little effect on the efficiency of the consortium blockchain, and has a good detection performance. The recall rate, precision and F1 value can reach 85.3%, 87.7% and 86.5% respectively.

Key words: blockchain, consortium blockchain, anomaly detection, privacy protection, KNN

中图分类号:

TP309

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.

CHEN Binjie, WEI Fushan, GU Chunxiang. Blockchain Abnormal Transaction Detection with Privacy-preserving Based on KNN[J]. Netinfo Security, 2022, 22(3): 78-84.

图/表 4

表1

表2

表3

表4

参考文献 14

[1]	ZHENG Zibin, XIE Shaoan, DAI Hongning, et al. An Overview of Blockchain Technology: Architecture, Consensus, and Future Trends [C]//IEEE. 5th IEEE International Congress on Big Data, June 25-30, 2017, Honolulu, HI, USA. New York: IEEE, 2017: 557-564.
[2]	XIE Junfeng, TANG H, HUANG Tao, et al. A Survey of Blockchain Technology Applied to Smart Cities: Research Issues and Challenges[J]. IEEE Communications Surveys & Tutorials, 2019, 21(3):2794-2830.
[3]	PHAM T, LEE S. Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods[EB/OL]. https://arxiv.org/abs/1611.03941v2, 2016-11-12.
[4]	PHAM T, LEE S. Anomaly Detection in the Bitcoin System-A Network Perspective[EB/OL]. https://arxiv.org/abs/1611.03942v1, 2016-11-12.
[5]	TOYODA K, OHTSUKI T, MATHIOPOULOS P T. Identification of High Yielding Investment Programs in Bitcoin via Transactions Pattern Analysis [C]//IEEE. 17th IEEE Global Communications Conference, December 4-8, 2017, Singapore. New York: IEEE, 2017: 1-6.
[6]	BARTOLETTI M, CARTA S, CIMOLI T, et al. Dissecting Ponzi Schemes on Ethereum: Identification, Analysis, Impact[EB/OL]. https://arxiv.org/abs/1703.03779v6, 2017-03-10.
[7]	VASEK M, MOORE T. Analyzing the Bitcoin Ponzi Scheme Ecosystem [C]//Springer. 22nd International Conference on Financial Cryptography and Data Security, February 26-March 2, 2018, Nieuwpoort, Curacao, Netherlands Antilles. Heidelberg: Springer, 2018: 101-112.
[8]	CHEN Weili, ZHENG Zibin, CUI Jiahui, et al. Detecting Ponzi Schemes on Ethereum: Towards Healthier Blockchain Technology [C]//ACM. 27th World Wide Web Conference, April 23-27, 2018, Lyon, France. New York: ACM, 2018: 1409-1418.
[9]	TORRES C F, STEICHEN M. The Art of the Scam: Demystifying Honeypots in Ethereum Smart Contracts [C]//USENIX. 28th USENIX Conference on Security Symposium, August 14-16, 2019, Santa Clara, CA, USA. Berkeley: USENIX, 2019: 1591-1607.
[10]	CHEN Weili, WU Jun, ZHENG Zibin, et al. Market Manipulation of Bitcoin: Evidence from Mining the Mt. Gox Transaction Network [C]//IEEE. 38th IEEE Conference on Computer Communications, April 29-May 2, 2019, Paris, France. New York: IEEE, 2019: 964-972.
[11]	OH B, JUN T J, YOON W, et al. Enhancing Trust of Supply Chain Using Blockchain Platform with Robust Data Model and Verification Mechanisms [C]//IEEE. 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), October 6-9, 2019, Bari, Italy. New York: IEEE, 2019: 3504-3511.
[12]	WANG Ziyu, LUO Nanqing, ZHOU Pan. GuardHealth: Blockchain Empowered Secure Data Management and Graph Convolutional Network Enabled Anomaly Detection in Smart Healthcare[J]. Journal of Parallel and Distributed Computing, 2020, 142(6):1-12. doi: 10.1016/j.jpdc.2020.03.004 URL
[13]	HUANG Dongyan, CHEN Bin, LI Lang, et al. Anomaly Detection for Consortium Blockchains Based on Machine Learning Classification Algorithm [C]//Springer. 9th International Conference on Computational Data and Social Networks, December 11-13, 2020, Dallas, TX, USA. Heidelberg: Springer, 2020: 307-318.
[14]	GARCIA S, DERRAC J, CANO J, et al. Prototype Selection for Nearest Neighbor Classification: Taxonomy and Empirical Study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3):417-435. doi: 10.1109/TPAMI.2011.142 URL

特征名称	特征描述
花费时间间隔	交易的最大输出花费的等待时间
交易输出方差	交易的所有输出金额的方差
小数点位数	交易的最大输出金额的小数点位数
输入交易花费时间间隔均值	交易的所有输入交易的花费时间间隔的平均值
输出交易花费时间间隔均值	交易的所有输出交易的花费时间间隔的平均值
输出交易花费时间间隔最大值	交易的所有输出交易的花费时间间隔的最大值
出度	交易的输出交易数量
入度	交易的输入交易数量
总金额	交易的总金额

方法名称	准确率	召回率	精度	F1
LOF	89.6%	0.5%	0.6%	0.6%
OCSVM	89.7%	0	0	—
MDB	89.5%	0	0	—
KNN	98.5%	85.3%	87.7%	86.5%

		计算复杂度	通信复杂度
		计算复杂度	带宽/bit	通信轮数/轮
数据上传阶段	联盟链	$O(p{{n}^{3}})$	$2pq{{(n+2)}^{2}}$	1
数据上传阶段	云服务器	可忽略	$2pq{{(n+2)}^{2}}$	1
异常检测阶段	联盟链	$O(m{{n}^{3}})$	$2mq{{(n+2)}^{2}}$	1
异常检测阶段	云服务器	$O(mp{{n}^{3}})$	$2mq{{(n+2)}^{2}}$	1
联盟链确认阶段	联盟链	可忽略	$4mq{{(n+2)}^{2}}$	2
联盟链确认阶段	云服务器	$O(m{{n}^{3}})$	$4mq{{(n+2)}^{2}}$	2

	带宽/MB	内存空间占用/MB	单特征向量耗时/ms
数据上传阶段	1.14	14.7	0.037
异常检测阶段	0.49	64.8	79.046

[1]	冯怡婷, 马兆丰, 徐单恒, 段鹏飞. 跨链接入的区块链安全强度评估方法[J]. 信息网络安全, 2023, 23(1): 84-92.
[2]	于晶, 袁曙光, 袁煜琳, 陈驰. 基于k匿名数据集的鲁棒性水印技术研究[J]. 信息网络安全, 2022, 22(9): 11-20.
[3]	张光华, 刘永升, 王鹤, 于乃文. 基于BiLSTM和注意力机制的智能合约漏洞检测方案[J]. 信息网络安全, 2022, 22(9): 46-54.
[4]	张学旺, 刘宇帆. 可追踪身份的物联网感知层节点匿名认证方案[J]. 信息网络安全, 2022, 22(9): 55-62.
[5]	胡艺, 佘堃. 基于区块链和智能合约的双链车联网系统[J]. 信息网络安全, 2022, 22(8): 26-35.
[6]	黄保华, 赵伟宏, 彭丽, 谢统义. 基于MPT索引的高效链上PKI模型[J]. 信息网络安全, 2022, 22(8): 72-80.
[7]	顾兆军, 刘婷婷, 高冰, 隋翯. 基于GAN-Cross的工控系统类不平衡数据异常检测[J]. 信息网络安全, 2022, 22(8): 81-89.
[8]	KELEKET GOMA Christy Junior Yannick, 易文哲, 王鹃. 一种基于SGX的轻量Fabric链码可信执行环境构建方法[J]. 信息网络安全, 2022, 22(7): 73-83.
[9]	秦宝东, 余沛航, 郑东. 基于双陷门同态加密的决策树分类模型[J]. 信息网络安全, 2022, 22(7): 9-17.
[10]	王姝爽, 马兆丰, 刘嘉微, 罗守山. 区块链跨链安全接入与身份认证方案研究与实现[J]. 信息网络安全, 2022, 22(6): 61-72.
[11]	于克辰, 郭莉, 阴宏伟, 燕雪松. 面向数据中心场景的基于区块链与博弈论的高价值数据共享模型[J]. 信息网络安全, 2022, 22(6): 73-85.
[12]	冯景瑜, 张琪, 黄文华, 韩刚. 基于跨链交互的网络安全威胁情报共享方案[J]. 信息网络安全, 2022, 22(5): 21-29.
[13]	刘嘉微, 马兆丰, 王姝爽, 罗守山. 基于区块链的隐私信用数据受限共享技术研究[J]. 信息网络安全, 2022, 22(5): 54-63.
[14]	周婧怡, 李红娇. 针对PMU测量的虚假数据注入攻击检测方法[J]. 信息网络安全, 2022, 22(5): 75-83.
[15]	崔皓宇, 马利民, 王佳慧, 张伟. 基于区块链的属性加密多授权机构安全模型研究[J]. 信息网络安全, 2022, 22(5): 84-93.

基于KNN的具有隐私保护功能的区块链异常交易检测

Blockchain Abnormal Transaction Detection with Privacy-preserving Based on KNN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 14

相关文章 15

编辑推荐

Metrics

本文评价