Article(id=1329458066220757618, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329457773609332873, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440477, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1717516800000, receivedDateStr=2024-06-05, revisedDate=1720886400000, revisedDateStr=2024-07-14, acceptedDate=null, acceptedDateStr=null, onlineDate=1794897103123, onlineDateStr=2026-11-17, pubDate=1727712000000, pubDateStr=2024-10-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794897103123, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794897103123, creator=13701087609, updateTime=1794897103123, updator=13701087609, issue=Issue{id=1329457773609332873, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='10', pageStart='2401', pageEnd='2661', issueExtLink='null', onlineDate='null', pubDate='1727712000000', pubDateStr='2024-10-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794897033359, creator='13701087609', updateTime=1794897033359, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=2526, endPage=2539, ext={EN=ArticleExt(id=1329458066459832947, articleId=1329458066220757618, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=An Accurate Blockchain Anomaly Detection Mechanism Built on Approximate Sketch Algorithms, columnId=1329457847257117432, journalTitle=Journal of Computer Research and Development, columnName=Privacy Preserving Based on Blockchain, runingTitle=null, highlight=null, articleAbstract=

Blockchain suffers from network dynamics and management difficulties, making the anomalies such as DDoS attacks and account takeovers possible. Existing approaches that detect anomalies in blockchains extract features, such as historical transaction information and transaction frequencies, from blockchain accounts to identify anomalies. However, the increasing scale of blockchain data results in the challenge of high memory consumption and low detection accuracy in the feature extraction of existing approaches. To address this challenge, we propose a blockchain anomaly detection mechanism that achieves detection accuracy and reduces resource footprints. This mechanism embraces approximate sketching algorithms to transform the detection of blockchain anomalies into that of malicious accounts, including intra-block accounts and inter-block accounts. For intra-block accounts, i.e., the malicious accounts that occur inside a single block and the mechanism uses sketching algorithms to collectively filter out those accounts with high precision. For inter-block accounts, malicious accounts can be hardly detected by analyzing the information of a single block, it aggregates multi-block information to accurately detect those accounts. We evaluate our mechanism with real Ethereum block data comprising of 88847 blocks. Our results indicate that compared with typical existing approaches, our mechanism improves the recall of detecting blockchain anomalies by up to 6.3 times and the F1 score by up to 4.4 times. Therefore, our proposed blockchain anomaly detection mechanism can bring benefits to regulating blockchain transaction behaviors and maintain system security.

, authors=Longlong Zhu1, 2, 5, Xiang Chen2, Haodong Chen1, Jitang Niu4, Wenjing Liu3, Shengrui Lin1, Dong Zhang1, 5, *, Chunming Wu2, 5, authorsList=Longlong Zhu, Xiang Chen, Haodong Chen, Jitang Niu, Wenjing Liu, Shengrui Lin, Dong Zhang, Chunming Wu, authorCompany=null, correspAuthors=Dong Zhang, authorNote=

born in 2000. Master candidate. His main research interests include network measurement, programmable networks, and packet classification

born in 1997. PhD candidate. His main research interests include programmable networks and network measurement

born in 2000. Master candidate. His main research interests include programmable networks and datacenter congestion control

born in 2002. Master candidate. His main research interests include network measurement and programmable networks

born in 1995. Bachelor. Her main research interests include convergence media network and network security

born in 1997. PhD candidate. His main research interests include programmable networks and in-network intelligence

born in 1981. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software defined networking, network virtualization and Internet QoS

born in 1967. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network architecture, Cyberspace Endogenous Safety and Security

, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1329458069869802141, articleId=1329458066220757618, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于近似测量算法Sketch的高精度区块链异常检测机制, columnId=1329457847403918074, journalTitle=计算机研究与发展, columnName=基于区块链的数据隐私保护, runingTitle=null, highlight=null, articleAbstract=

区块链存在网络动态性强和其管理困难等问题,使得区块链普遍存在DDoS 攻击和账户接管等异常现象. 现有区块链异常检测方法多从所有区块链账户中提取历史交易信息和交易频率等特征加以分析以甄别异常. 然而,随着区块链数据规模的不断扩大,现有方法在提取特征时面临内存消耗高、检测精度低的挑战. 为此,提出了一种高检测精度、低内存开销的区块链异常检测机制,该机制采用近似测量算法将区块链异常检测转化为异常交易账户检测,包括区块内异常账户和跨区块异常账户. 对于区块内异常账户,即仅存在于单个区块内的异常账户,使用Sketch算法进行账户识别,精度高. 而对于存在于多个区块且难以通过单个区块信息检测到的跨区块异常账户,则通过聚合和分析多区块信息进行账户的准确检测. 使用包含88 847个区块的真实区块链数据评估上述机制. 实验结果表明,与现有代表性方法对比,所提出的机制将区块链异常检测的召回率最高提升了6.3倍,F1分数最高提升了4.4倍. 因此,提出的高精度区块链异常检测机制对于规范区块链交易行为、维护系统安全性具有意义.

, authors=朱龙隆1, 2, 5, 陈翔2, 陈浩东1, 牛继堂4, 刘雯靓3, 林声睿1, 张栋1, 5, *, 吴春明2, 5, authorsList=朱龙隆, 陈翔, 陈浩东, 牛继堂, 刘雯靓, 林声睿, 张栋, 吴春明, authorCompany=null, correspAuthors=张栋, authorNote=

2000年生. 硕士研究生. 主要研究方向为网络测量、可编程网络、包分类

1997年生. 博士研究生. 主要研究方向为可编程网络、网络测量

2000年生. 硕士研究生. 主要研究方向为可编程网络、数据中心拥塞控制

2002年生. 硕士研究生. 主要研究方向为网络测量、可编程网络

1995年生. 学士. 主要研究方向为融合媒体网络、网络安全

1997年生. 博士研究生. 主要研究方向为可编程网络、网内智能

1981年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为软件定义网络、网络虚拟化、网络服务质量

1967 年生. 博士,教授,博士生导师,CCF 会员. 主要研究方向为网络体系结构、网络空间内生安全

, correspAuthorsNote=
张栋()
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=uUZ5pcODzt+32xMi4Vj93w==, magXml=tWbioAyEhx/rbo2EJIhOVQ==, pdfUrl=null, pdf=SD7CrMmzf8UWZtm+mgxPRA==, pdfFileSize=2564087, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=xjHIzrPBmmXyejHaguQ6EQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=xnSZX3Gbxdn4Egt5+UUk0A==, mapNumber=null, fund=null)}, authors=[Author(id=1329458070540890798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=kikionepin@gmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458070628971186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070540890798, language=EN, stringName=Longlong Zhu, firstName=Longlong, middleName=null, lastName=Zhu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 5, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013
5Quan Cheng Laboratory, Jinan 250103, bio={"content":"

born in 2000. Master candidate. His main research interests include network measurement, programmable networks, and packet classification

"}, bioImg=null, bioContent=

born in 2000. Master candidate. His main research interests include network measurement, programmable networks, and packet classification

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458070700274355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070540890798, language=CN, stringName=朱龙隆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 5, address=1福州大学计算机与大数据学院 福州 350108
2浙江大学计算机科学与技术学院 杭州 310013
5泉城实验室 济南 250103, bio={"img":"PYWUVIc4NErJ3XO0jK6I0Q==","content":"

2000年生. 硕士研究生. 主要研究方向为网络测量、可编程网络、包分类

"}, bioImg=PYWUVIc4NErJ3XO0jK6I0Q==, bioContent=

2000年生. 硕士研究生. 主要研究方向为网络测量、可编程网络、包分类

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)]), AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])]), Author(id=1329458070763188917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458070830297783, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070763188917, language=EN, stringName=Xiang Chen, firstName=Xiang, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1997. PhD candidate. His main research interests include programmable networks and network measurement

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include programmable networks and network measurement

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458070893212344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070763188917, language=CN, stringName=陈翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2浙江大学计算机科学与技术学院 杭州 310013, bio={"img":"E770sk+jFdVDD+PGCOlt/A==","content":"

1997年生. 博士研究生. 主要研究方向为可编程网络、网络测量

"}, bioImg=E770sk+jFdVDD+PGCOlt/A==, bioContent=

1997年生. 博士研究生. 主要研究方向为可编程网络、网络测量

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)])]), Author(id=1329458070972904122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071044207292, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070972904122, language=EN, stringName=Haodong Chen, firstName=Haodong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108, bio={"content":"

born in 2000. Master candidate. His main research interests include programmable networks and datacenter congestion control

"}, bioImg=null, bioContent=

born in 2000. Master candidate. His main research interests include programmable networks and datacenter congestion control

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071123899069, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070972904122, language=CN, stringName=陈浩东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1福州大学计算机与大数据学院 福州 350108, bio={"img":"kJBaz1FQvskYAkFEE0+CFQ==","content":"

2000年生. 硕士研究生. 主要研究方向为可编程网络、数据中心拥塞控制

"}, bioImg=kJBaz1FQvskYAkFEE0+CFQ==, bioContent=

2000年生. 硕士研究生. 主要研究方向为可编程网络、数据中心拥塞控制

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)])]), Author(id=1329458071178425023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071249728193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071178425023, language=EN, stringName=Jitang Niu, firstName=Jitang, middleName=null, lastName=Niu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4Polytechnic Institute of Zhejiang University, Hangzhou 310015, bio={"content":"

born in 2002. Master candidate. His main research interests include network measurement and programmable networks

"}, bioImg=null, bioContent=

born in 2002. Master candidate. His main research interests include network measurement and programmable networks

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071321031362, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071178425023, language=CN, stringName=牛继堂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4浙江大学工程师学院 杭州 310015, bio={"img":"fpd8EkW4thUa4cJuqEF8tw==","content":"

2002年生. 硕士研究生. 主要研究方向为网络测量、可编程网络

"}, bioImg=fpd8EkW4thUa4cJuqEF8tw==, bioContent=

2002年生. 硕士研究生. 主要研究方向为网络测量、可编程网络

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070410867367, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=4, ext=[AuthorCompanyExt(id=1329458070419255976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070410867367, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Polytechnic Institute of Zhejiang University, Hangzhou 310015), AuthorCompanyExt(id=1329458070427644585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070410867367, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4浙江大学工程师学院 杭州 310015)])]), Author(id=1329458071379751620, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071451054790, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071379751620, language=EN, stringName=Wenjing Liu, firstName=Wenjing, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Zhejiang Media Group, Hangzhou 310005, bio={"content":"

born in 1995. Bachelor. Her main research interests include convergence media network and network security

"}, bioImg=null, bioContent=

born in 1995. Bachelor. Her main research interests include convergence media network and network security

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071526552263, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071379751620, language=CN, stringName=刘雯靓, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3浙江广播电视集团 杭州 310005, bio={"img":"/gfh34dT05u75nA4upb7WA==","content":"

1995年生. 学士. 主要研究方向为融合媒体网络、网络安全

"}, bioImg=/gfh34dT05u75nA4upb7WA==, bioContent=

1995年生. 学士. 主要研究方向为融合媒体网络、网络安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070318592676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=3, ext=[AuthorCompanyExt(id=1329458070326981285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070318592676, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Zhejiang Media Group, Hangzhou 310005), AuthorCompanyExt(id=1329458070335369894, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070318592676, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3浙江广播电视集团 杭州 310005)])]), Author(id=1329458071602049738, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071694324428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071602049738, language=EN, stringName=Shengrui Lin, firstName=Shengrui, middleName=null, lastName=Lin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108, bio={"content":"

born in 1997. PhD candidate. His main research interests include programmable networks and in-network intelligence

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include programmable networks and in-network intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071769821901, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071602049738, language=CN, stringName=林声睿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1福州大学计算机与大数据学院 福州 350108, bio={"img":"5QH1kmAdmEm80VS/+zH3Fg==","content":"

1997年生. 博士研究生. 主要研究方向为可编程网络、网内智能

"}, bioImg=5QH1kmAdmEm80VS/+zH3Fg==, bioContent=

1997年生. 博士研究生. 主要研究方向为可编程网络、网内智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)])]), Author(id=1329458071836930767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangdong@fzu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329458072050840274, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071836930767, language=EN, stringName=Dong Zhang, firstName=Dong, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 5, *, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108
5Quan Cheng Laboratory, Jinan 250103, bio={"content":"

born in 1981. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software defined networking, network virtualization and Internet QoS

"}, bioImg=null, bioContent=

born in 1981. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software defined networking, network virtualization and Internet QoS

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458072176669395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071836930767, language=CN, stringName=张栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 5, *, address=1福州大学计算机与大数据学院 福州 350108
5泉城实验室 济南 250103, bio={"img":"LYMChngqkUFUDkxjwQYBxQ==","content":"

1981年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为软件定义网络、网络虚拟化、网络服务质量

"}, bioImg=LYMChngqkUFUDkxjwQYBxQ==, bioContent=

1981年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为软件定义网络、网络虚拟化、网络服务质量

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])]), Author(id=1329458072319275734, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458072508019418, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458072319275734, language=EN, stringName=Chunming Wu, firstName=Chunming, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 5, address=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013
5Quan Cheng Laboratory, Jinan 250103, bio={"content":"

born in 1967. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network architecture, Cyberspace Endogenous Safety and Security

"}, bioImg=null, bioContent=

born in 1967. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network architecture, Cyberspace Endogenous Safety and Security

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458072621265628, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458072319275734, language=CN, stringName=吴春明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 5, address=2浙江大学计算机科学与技术学院 杭州 310013
5泉城实验室 济南 250103, bio={"img":"nwtaBtUoI99JKCabnL5b0g==","content":"

1967 年生. 博士,教授,博士生导师,CCF 会员. 主要研究方向为网络体系结构、网络空间内生安全

"}, bioImg=nwtaBtUoI99JKCabnL5b0g==, bioContent=

1967 年生. 博士,教授,博士生导师,CCF 会员. 主要研究方向为网络体系结构、网络空间内生安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])])], keywords=[Keyword(id=1329458072705151709, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, orderNo=1, keyword=blockchain), Keyword(id=1329458072793232094, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, orderNo=2, keyword=security), Keyword(id=1329458072881312479, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, orderNo=3, keyword=anomaly detection), Keyword(id=1329458073099416288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, orderNo=4, keyword=approximate algorithms), Keyword(id=1329458073174913761, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, orderNo=5, keyword=Sketch), Keyword(id=1329458073304937186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, orderNo=1, keyword=区块链), Keyword(id=1329458073367851747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, orderNo=2, keyword=安全), Keyword(id=1329458073464320740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, orderNo=3, keyword=异常检测), Keyword(id=1329458073539818213, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, orderNo=4, keyword=近似算法), Keyword(id=1329458073611121382, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, orderNo=5, keyword=Sketch)], refs=[Reference(id=1329458077608293138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Wood G. Ethereum: A secure decentralised generalised transaction ledger[J]. Ethereum Project Yellow Paper, 2014, 151(2014): 1−32, articleTitle=null, refAbstract=null), Reference(id=1329458077692179219, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Wright C S. Bitcoin: A peer-to-peer electronic cash system[J]. SSRN Electronic Journal, 2008, 3440802: 10−2139, articleTitle=null, refAbstract=null), Reference(id=1329458077784453908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=韩璇,袁勇,王飞跃. 区块链安全问题:研究现状与展望[J]. 自动化学报,2019,45(1):206−225, articleTitle=null, refAbstract=null), Reference(id=1329458077851562773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Xuan, Yuan Yong, Wang Feiyue. Security problems on blockchain: The state of the art and future trends[J]. Acta Automatica Sinica, 2019, 45(1): 206−225 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458077922865942, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=江沛佩,王骞,陈艳姣,等. 区块链网络安全保障:攻击与防御[J]. 通信学报,2021,42(1):151−162, articleTitle=null, refAbstract=null), Reference(id=1329458077989974807, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Peipei, Wang Qian, Chen Yanjiao, et al. Securing guarantee of the blockchain network: Attacks and countermeasures[J]. Journal on Communications, 2021, 42(1): 151−162 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458078048695064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Antonopoulos A M. Mastering Bitcoin: Unlocking Ddigital Cryptocurrencies[M]. Sebastopol: O'Reilly Media, 2017, articleTitle=null, refAbstract=null), Reference(id=1329458078115803929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=叶聪聪,李国强,蔡鸿明,等. 区块链的安全检测模型[J]. 软件学报,2018,29(5):1348−1359, articleTitle=null, refAbstract=null), Reference(id=1329458078191301402, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Congcong, Li Guoqiang, Cai Hongming, et al. Security detection model of blockchain[J]. Journal of Software, 2018, 29(5): 1348−1359 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458078291964699, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=曾诗钦,霍如,黄韬,等. 区块链技术研究综述:原理、进展与应用[J]. 通信学报,2020,41(1):134−151, articleTitle=null, refAbstract=null), Reference(id=1329458078371656476, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Zeng Shiqin, Huo Ru, Huang Tao, et al. Survey of blockchain: Principle, progress and application[J]. Journal on Communications, 2020, 41(1): 134−151 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458078468125469, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Hassan M U, Rehmani M H, Chen Jinjun. Anomaly detection in blockchain networks: A comprehensive survey[J]. arXiv Preprint, arXiv: 2112.06089, 2021, articleTitle=null, refAbstract=null), Reference(id=1329458078552011550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim J, Nakashima M, Fan W J, et al. Anomaly detection based on traffic monitoring for secure blockchain networking[C]//Proc of the 2021 IEEE Int Conf on Blockchain and Cryptocurrency (ICBC). Piscataway, NJ : IEEE , 2021: 1−9, articleTitle=null, refAbstract=null), Reference(id=1329458078627509023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Zwang M, Somin S, Pentland A S, et al. Detecting bot activity in the Ethereum blockchain network[J]. arXiv preprint, arXiv: 1810.01591, 2018, articleTitle=null, refAbstract=null), Reference(id=1329458078690423584, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Weili, Zheng Zibin, Ngai E, et al. Exploiting blockchain data to detect smart Ponzi schemes on ethereum[J]. IEEE Access, 2019, 7: 37575−37586, articleTitle=null, refAbstract=null), Reference(id=1329458078761726753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Case J, Fedor M, Schoffstall M, et al. A simple network management protocol (SNMP)[EB/OL]. (1990-05-02)[2024-07-13]. https://www.ietf.org/rfc/rfc1157.txt, articleTitle=null, refAbstract=null), Reference(id=1329458078824641314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Claise B. NetFlow[EB/OL]. (2004-10-02)[2024-07-13]. https://www.ietf.org/rfc/rfc3954.txt, articleTitle=null, refAbstract=null), Reference(id=1329458078895944483, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Phaal P, Panchen S, McKee N. sFlow[EB/OL]. (2001-09-02)[2024-07-13]. https://www.ietf.org/rfc/rfc3176.txt, articleTitle=null, refAbstract=null), Reference(id=1329458078958859044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Suh J, Kwon T T, Dixon C, et al. OpenSample: A low-latency, sampling-based measurement platform for commodity SDN[C]//Proc of the 2014 Int Conf on Distributed Computing Systems. Piscataway, NJ: IEEE, 2014: 228−237, articleTitle=null, refAbstract=null), Reference(id=1329458079072105254, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Eliyan L F, Pietro R D. DoS and DDoS attacks in software defined networks: A survey of existing solutions and research challenges[J]. Future Generation Computer Systems, 2021, 122: 149−171, articleTitle=null, refAbstract=null), Reference(id=1329458079193740071, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Mirkin M, Ji Y, Pang J, et al. Bdos: Blockchain denial of service[C]//Proc of the 2020 ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2020: 601−619, articleTitle=null, refAbstract=null), Reference(id=1329458079302791976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Weili, Zheng Zibin, Cui Jiahui, et al. Detecting Ponzi schemes on ethereum: Towards healthier blockchain technology[C]//Proc of the 2018 World Wide Web Conf. New York: ACM, 2018: 1409−1418, articleTitle=null, refAbstract=null), Reference(id=1329458079445398313, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Andryukhin A A. Phishing attacks and preventions in blockchain based projects[C]//Proc of the 2019 Int Conf on Engineering Technologies and Computer Science. Piscataway, NJ: IEEE, 2019: 15−19, articleTitle=null, refAbstract=null), Reference(id=1329458079608976170, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Chainalysis. Israeli government seizes cryptocurrency addresses associated with Hamas donation campaigns[EB/OL]. (2021-07-08)[2024-07-13]. https://blog.chainalysis.com/reports/israel-hamas-cryptocurrency-seizure-july-2021, articleTitle=null, refAbstract=null), Reference(id=1329458079814497067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Voronov T, Raz D, Rottenstreich O. A framework for anomaly detection in blockchain networks with sketches[J]. IEEE/ACM Transactions on Networking, 2024, 1(32): 686−698, articleTitle=null, refAbstract=null), Reference(id=1329458079927743276, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Barabasi A L. The origin of bursts and heavy tails in human dynamics[J]. Nature, 2005, 435(7039): 207−211, articleTitle=null, refAbstract=null), Reference(id=1329458080020017965, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Xuanchen, Yang Wenzhong, Tian Xiaodan. Detecting phishing accounts on Ethereum based on transaction records and EGAT[J]. Electronics, 2023, 12(4): 993, articleTitle=null, refAbstract=null), Reference(id=1329458080372339503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Voronov T, Raz D, Rottenstreich O. Scalable blockchain anomaly detection with sketches[C]//Proc of the 2021 IEEE Int Conf on Blockchain. Piscataway: IEEE, 2021: 1−10, articleTitle=null, refAbstract=null), Reference(id=1329458080502362928, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Lu, Huang Qun, Lee P P C. MV-Sketch: A past and compact invertible sketch for heavy flow detection in network data streams[C]//Proc of the 2019 IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2019: 2026−2034, articleTitle=null, refAbstract=null), Reference(id=1329458080728855345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Jie, Zhang Zheng, Chen Hongchang, et al. Filter-Sketch: A two-layer sketch for entropy estimation in the data plane[J]. IET Communications, 2022, 16(20): 2422−2430, articleTitle=null, refAbstract=null), Reference(id=1329458080909210418, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Rush T J. Enhanced adaptive Bloom filters for identifying transactions of interest in a blockchain[R/OL]. New York: QuickBlocks, 2017[2020-06-05]. http://quickblocks.io, articleTitle=null, refAbstract=null), Reference(id=1329458081039233843, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Qin Kaihua, Hadass H, Gervais A, et al. Applying private information retrieval to lightweight bitcoin clients[C]//Proc of the 15th Crypto Valley Conf on Blockchain Technology (CVCBT). Piscataway, NJ: IEEE, 2019: 60−72, articleTitle=null, refAbstract=null), Reference(id=1329458081131508532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Tianyu, Zhu Wenbin, Ma Qun, et al. ABACUS: Address-partitioned Bloom filter on address checking for uniqueness in IoT blockchain[C]//Proc of the 39th Int Conf on Computer-Aided Design. Virtual Event, USA: ACM 2020: 1−7, articleTitle=null, refAbstract=null), Reference(id=1329458081211200309, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Shafeeq S, Zeadally S, Alam M, et al. Curbing address reuse in the IOTA distributed ledger: A cuckoo-filter-based approach[J]. IEEE Transactions on Engineering Management, 2019, 67(4): 1244−1255, articleTitle=null, refAbstract=null), Reference(id=1329458081395749686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Rottenstreich O. Sketches for blockchains[C]//Proc of the 2021 Int Conf on Communication Systems & Networks. Piscataway, NJ: IEEE, 2021: 254−262, articleTitle=null, refAbstract=null), Reference(id=1329458081517384504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Yibing, Huang C C, Tsai S C. SDN soft computing application for detecting heavy hitters[J]. IEEE Transactions on Industrial Informatics, 2019, 15(10): 5690−5699, articleTitle=null, refAbstract=null), Reference(id=1329458081592881977, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Reviriego P, Martínez J, Rottenstreich O, et al. Remove minimum (RM): An error-tolerant scheme for cardinality estimate by HyperLogLog[J]. IEEE Transactions on Dependable and Secure Computing, 2020, 19(2): 966−977, articleTitle=null, refAbstract=null), Reference(id=1329458081659990842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Etherscan. The Ethereum blockchain explorer[EB/OL]. (2024-06-02)[2024-07-13]. https://etherscan.io, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)]), AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)]), AuthorCompany(id=1329458070318592676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=3, ext=[AuthorCompanyExt(id=1329458070326981285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070318592676, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Zhejiang Media Group, Hangzhou 310005), AuthorCompanyExt(id=1329458070335369894, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070318592676, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3浙江广播电视集团 杭州 310005)]), AuthorCompany(id=1329458070410867367, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=4, ext=[AuthorCompanyExt(id=1329458070419255976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070410867367, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Polytechnic Institute of Zhejiang University, Hangzhou 310015), AuthorCompanyExt(id=1329458070427644585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070410867367, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4浙江大学工程师学院 杭州 310015)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])], figs=[ArticleFig(id=1329458073757922023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 1, caption=Workflow of Sketch-based anomaly accounts detection in blockchain, figureFileSmall=7i8fTD0MN089BBp0ZZqsxg==, figureFileBig=xjHIzrPBmmXyejHaguQ6EQ==, tableContent=null), ArticleFig(id=1329458073858585320, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图1, caption=基于Sketch的区块链异常账户检测工作流程, figureFileSmall=7i8fTD0MN089BBp0ZZqsxg==, figureFileBig=xjHIzrPBmmXyejHaguQ6EQ==, tableContent=null), ArticleFig(id=1329458074127020777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 2, caption=HashPipe-based dual-stage anomaly accounts detection, figureFileSmall=D0y+lOQYHombNHDrMei1cQ==, figureFileBig=dpNPvMOt9Z7RepEE1SIp1A==, tableContent=null), ArticleFig(id=1329458074210906858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图2, caption=基于HashPipe的异常账户两阶段检测, figureFileSmall=D0y+lOQYHombNHDrMei1cQ==, figureFileBig=dpNPvMOt9Z7RepEE1SIp1A==, tableContent=null), ArticleFig(id=1329458074298987243, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 3, caption=HyperLogLog-based detection of anomaly accounts with high out-degree, figureFileSmall=thznNgAgqkv/0pR5N8citA==, figureFileBig=Vo3N4xvlSGZLUXXzByL6Sw==, tableContent=null), ArticleFig(id=1329458074361901804, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图3, caption=基于HyperLogLog的高出度异常账户检测, figureFileSmall=thznNgAgqkv/0pR5N8citA==, figureFileBig=Vo3N4xvlSGZLUXXzByL6Sw==, tableContent=null), ArticleFig(id=1329458074454176493, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 4, caption=Average precision and average recall rate of detection for high out-degree anomaly accounts, figureFileSmall=PSHW1dzH90Mypn7unmNg1g==, figureFileBig=P79pq9Qn4qppek5C3A9h2A==, tableContent=null), ArticleFig(id=1329458074600977134, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图4, caption=高出度异常账户检测的平均精度和平均召回率, figureFileSmall=PSHW1dzH90Mypn7unmNg1g==, figureFileBig=P79pq9Qn4qppek5C3A9h2A==, tableContent=null), ArticleFig(id=1329458074668085999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 5, caption=Average precision and average recall rate of detection for high out-degree anomaly accounts introducing with factor, figureFileSmall=tp5RjGY4/Zp1F3WR/bykjA==, figureFileBig=b7EI9vLPmqw5CSjiAOOhSQ==, tableContent=null), ArticleFig(id=1329458074869412592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图5, caption=引入$ f actor $的高出度异常账户检测平均精度和平均召回率, figureFileSmall=tp5RjGY4/Zp1F3WR/bykjA==, figureFileBig=b7EI9vLPmqw5CSjiAOOhSQ==, tableContent=null), ArticleFig(id=1329458074953298673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 6, caption=Average recall rate of detection for anomaly accounts in DDoS dataset, figureFileSmall=Tg+UMGQY6nyWTYZb45e4Dw==, figureFileBig=JM6BtAadTYb7TVyd6/np8w==, tableContent=null), ArticleFig(id=1329458075028796146, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图6, caption=DDoS数据集下异常账户检测平均召回率, figureFileSmall=Tg+UMGQY6nyWTYZb45e4Dw==, figureFileBig=JM6BtAadTYb7TVyd6/np8w==, tableContent=null), ArticleFig(id=1329458075087516403, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 7, caption=Average recall rate and memory overhead of detection for high transaction volume anomaly accounts of different methods, figureFileSmall=7IdfhfeUdZ1hoVXHJuUA9g==, figureFileBig=3Mdh/qspXcnjXH2BPURzkg==, tableContent=null), ArticleFig(id=1329458075150430964, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图7, caption=不同方法的高交易额异常账户检测平均召回率和内存开销, figureFileSmall=7IdfhfeUdZ1hoVXHJuUA9g==, figureFileBig=3Mdh/qspXcnjXH2BPURzkg==, tableContent=null), ArticleFig(id=1329458075251094261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 8, caption=Average F1 score and memory overhead of detection for high transaction volume anomaly accounts of different methods, figureFileSmall=NnyCLu48BDxhGWBHir3gdg==, figureFileBig=KPXSjOzNLQVDCWuN6k0nmQ==, tableContent=null), ArticleFig(id=1329458075309814518, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图8, caption=不同方法的高交易额异常账户检测平均F1分数和内存开销, figureFileSmall=NnyCLu48BDxhGWBHir3gdg==, figureFileBig=KPXSjOzNLQVDCWuN6k0nmQ==, tableContent=null), ArticleFig(id=1329458075364340471, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 9, caption=Average rate recall and memory overhead of detection for high transaction frequencies anomaly accounts of different methods, figureFileSmall=+I7QsC0spHwJ4PwjSeoR/A==, figureFileBig=tavZVj6+eoMxhWR8h/0ePw==, tableContent=null), ArticleFig(id=1329458075460809464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图9, caption=不同方法的高交易频率异常账户检测平均召回率和内存开销, figureFileSmall=+I7QsC0spHwJ4PwjSeoR/A==, figureFileBig=tavZVj6+eoMxhWR8h/0ePw==, tableContent=null), ArticleFig(id=1329458075548889849, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 10, caption=Average F1 score and memory overhead of detection for high transaction frequencies anomaly accounts of different methods, figureFileSmall=+FLO6ZdlHPip8x4TKkJ6Og==, figureFileBig=1ftsqQCGKmIzmKg4lFoUNQ==, tableContent=null), ArticleFig(id=1329458075611804410, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图10, caption=不同方法高交易频率异常账户检测平均F1分数和内存开销, figureFileSmall=+FLO6ZdlHPip8x4TKkJ6Og==, figureFileBig=1ftsqQCGKmIzmKg4lFoUNQ==, tableContent=null), ArticleFig(id=1329458075674718971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 11, caption=Average recall rate and memory overhead of detection for high out-degree anomaly accounts of different methods, figureFileSmall=EiA6FgZSaUUhz4JlU0dmiQ==, figureFileBig=CMhi26IBrleOridE5zba7w==, tableContent=null), ArticleFig(id=1329458075750216444, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图11, caption=不同方法的高出度异常账户检测平均召回率和内存开销, figureFileSmall=EiA6FgZSaUUhz4JlU0dmiQ==, figureFileBig=CMhi26IBrleOridE5zba7w==, tableContent=null), ArticleFig(id=1329458075829908221, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Figure 12, caption=Average F1 score and memory overhead of detection for high out-degree anomaly accounts of different methods, figureFileSmall=QxZ4m2xu2FspFyceN8OQ9g==, figureFileBig=UEFZ8mNktdOQTi2GLJbWGw==, tableContent=null), ArticleFig(id=1329458075880239870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=图12, caption=不同方法的高出度异常账户检测平均F1分数和内存开销, figureFileSmall=QxZ4m2xu2FspFyceN8OQ9g==, figureFileBig=UEFZ8mNktdOQTi2GLJbWGw==, tableContent=null), ArticleFig(id=1329458075997680383, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 1, caption=

Comparison of Anomaly Detection Effect for Blockchain

, figureFileSmall=null, figureFileBig=null, tableContent=
算法类型内存开销准确度
静态规则检测方法高O(100 KB)~
O(1 MB)
高(召回率为100%、
F1分数为1)
采样检测方法低O(10 KB)低(召回率为15%~80%、
F1分数为0.22~0.64)
本文提出的检测机制低O(0.1 KB)高(召回率为95%、
F1分数为0.97)
), ArticleFig(id=1329458076073177856, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表1, caption=

区块链异常检测效果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
算法类型内存开销准确度
静态规则检测方法高O(100 KB)~
O(1 MB)
高(召回率为100%、
F1分数为1)
采样检测方法低O(10 KB)低(召回率为15%~80%、
F1分数为0.22~0.64)
本文提出的检测机制低O(0.1 KB)高(召回率为95%、
F1分数为0.97)
), ArticleFig(id=1329458076148675329, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 2, caption=

Notion of Symbols

, figureFileSmall=null, figureFileBig=null, tableContent=
符号含义
T高交易额、高交易频率异常账户检测中的阈值
C区块链交易账户
ValueC账户总交易额
CountC账户总交易次数
TotalValue总交易额
TotalCount总交易次数
DegC账户C的交易对象数量
$ \theta $高交易对象数量异常账户检测中的阈值
factor阈值$ \theta $的调整因子
), ArticleFig(id=1329458076253532930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表2, caption=

符号含义

, figureFileSmall=null, figureFileBig=null, tableContent=
符号含义
T高交易额、高交易频率异常账户检测中的阈值
C区块链交易账户
ValueC账户总交易额
CountC账户总交易次数
TotalValue总交易额
TotalCount总交易次数
DegC账户C的交易对象数量
$ \theta $高交易对象数量异常账户检测中的阈值
factor阈值$ \theta $的调整因子
), ArticleFig(id=1329458076337419011, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 3, caption=

Analysis of Account Transaction Volume

, figureFileSmall=null, figureFileBig=null, tableContent=
账户交易金额/ETH账户数量占数据集账户总数的比例/%
052489533.9539
≤1117131475.7689
≤10145012393.8043
≤100153012998.9796
账户交易额平均值:9.86142 ETH
), ArticleFig(id=1329458076475831044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表3, caption=

账户交易额分析

, figureFileSmall=null, figureFileBig=null, tableContent=
账户交易金额/ETH账户数量占数据集账户总数的比例/%
052489533.9539
≤1117131475.7689
≤10145012393.8043
≤100153012998.9796
账户交易额平均值:9.86142 ETH
), ArticleFig(id=1329458076614243077, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 4, caption=

Analysis of Account Transaction Frequencies

, figureFileSmall=null, figureFileBig=null, tableContent=
账户交易次数账户数量占数据集账户总数的比例/%
1102078566.0165
≤2126994782.1303
≤10150415797.2772
≤100154245399.7539
账户交易次数:5.62983
), ArticleFig(id=1329458076698129158, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表4, caption=

账户交易频率分析

, figureFileSmall=null, figureFileBig=null, tableContent=
账户交易次数账户数量占数据集账户总数的比例/%
1102078566.0165
≤2126994782.1303
≤10150415797.2772
≤100154245399.7539
账户交易次数:5.62983
), ArticleFig(id=1329458076819763975, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 5, caption=

Analysis of Account Out-Degree

, figureFileSmall=null, figureFileBig=null, tableContent=
账户出度账户数量占数据集账户总数的比例/%
1122315779.1394
≤3147061095.1499
≤10153529199.3348
≤20154179899.7558
≤50154406499.9024
≤100154468199.9424
≤1000154544199.9915
账户出度个数平均值:2.17878
), ArticleFig(id=1329458076899455753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表5, caption=

账户出度分析

, figureFileSmall=null, figureFileBig=null, tableContent=
账户出度账户数量占数据集账户总数的比例/%
1122315779.1394
≤3147061095.1499
≤10153529199.3348
≤20154179899.7558
≤50154406499.9024
≤100154468199.9424
≤1000154544199.9915
账户出度个数平均值:2.17878
), ArticleFig(id=1329458076966564618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 6, caption=

Average Recall Rates of High Transaction Volume Anomaly Accounts Detection %

, figureFileSmall=null, figureFileBig=null, tableContent=
HashPipe层数阈值T
5×10–410–35×10–310–2
220222935
435385059
648526777
857617787
1065708693
1272769197
14778295100
), ArticleFig(id=1329458077075616523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表6, caption=

高交易额异常账户检测的平均召回率

, figureFileSmall=null, figureFileBig=null, tableContent=
HashPipe层数阈值T
5×10–410–35×10–310–2
220222935
435385059
648526777
857617787
1065708693
1272769197
14778295100
), ArticleFig(id=1329458077230805772, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 7, caption=

Average Recall Rates of High Transaction Frequencies Anomaly Accounts Detection %

, figureFileSmall=null, figureFileBig=null, tableContent=
HashPipe层数阈值T
2×10–37×10–310–22×10–2
28141928
414233044
620303954
826364660
1030425264
1235475667
1439516068
), ArticleFig(id=1329458077323080462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表7, caption=

高交易频率异常账户检测的平均召回率

, figureFileSmall=null, figureFileBig=null, tableContent=
HashPipe层数阈值T
2×10–37×10–310–22×10–2
28141928
414233044
620303954
826364660
1030425264
1235475667
1439516068
), ArticleFig(id=1329458077419549456, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=EN, label=Table 8, caption=

Average Recall Rates of High Transaction Frequencies Anomaly Accounts Detection in 50 Blocks %

, figureFileSmall=null, figureFileBig=null, tableContent=
HashPipe层数阈值T
2×10–37×10–310–22×10–2
276959799
485989899
6929999100
8939999100
10959999100
129699100100
149799100100
), ArticleFig(id=1329458077499241233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, language=CN, label=表8, caption=

50个区块下高交易频率异常账户检测的平均召回率

, figureFileSmall=null, figureFileBig=null, tableContent=
HashPipe层数阈值T
2×10–37×10–310–22×10–2
276959799
485989899
6929999100
8939999100
10959999100
129699100100
149799100100
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440477, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440477, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440477, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440477, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1727712000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于近似测量算法Sketch的高精度区块链异常检测机制
朱龙隆 1, 2, 5 , 陈翔 2 , 陈浩东 1 , 牛继堂 4 , 刘雯靓 3 , 林声睿 1 , 张栋 1, 5, * , 吴春明 2, 5
计算机研究与发展 | 基于区块链的数据隐私保护 2024,61(10): 2526-2539
收起
收藏切换
计算机研究与发展 |基于区块链的数据隐私保护 2024 , 61 (10) : 2526 -2539
基于近似测量算法Sketch的高精度区块链异常检测机制
全屏
[Author(id=1329458070540890798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=kikionepin@gmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458070628971186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070540890798, language=EN, stringName=Longlong Zhu, firstName=Longlong, middleName=null, lastName=Zhu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 5, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108
2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013
5Quan Cheng Laboratory, Jinan 250103, bio={"content":"

born in 2000. Master candidate. His main research interests include network measurement, programmable networks, and packet classification

"}, bioImg=null, bioContent=

born in 2000. Master candidate. His main research interests include network measurement, programmable networks, and packet classification

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458070700274355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070540890798, language=CN, stringName=朱龙隆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 5, address=1福州大学计算机与大数据学院 福州 350108
2浙江大学计算机科学与技术学院 杭州 310013
5泉城实验室 济南 250103, bio={"img":"PYWUVIc4NErJ3XO0jK6I0Q==","content":"

2000年生. 硕士研究生. 主要研究方向为网络测量、可编程网络、包分类

"}, bioImg=PYWUVIc4NErJ3XO0jK6I0Q==, bioContent=

2000年生. 硕士研究生. 主要研究方向为网络测量、可编程网络、包分类

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)]), AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])]), Author(id=1329458070763188917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458070830297783, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070763188917, language=EN, stringName=Xiang Chen, firstName=Xiang, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013, bio={"content":"

born in 1997. PhD candidate. His main research interests include programmable networks and network measurement

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include programmable networks and network measurement

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458070893212344, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070763188917, language=CN, stringName=陈翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2浙江大学计算机科学与技术学院 杭州 310013, bio={"img":"E770sk+jFdVDD+PGCOlt/A==","content":"

1997年生. 博士研究生. 主要研究方向为可编程网络、网络测量

"}, bioImg=E770sk+jFdVDD+PGCOlt/A==, bioContent=

1997年生. 博士研究生. 主要研究方向为可编程网络、网络测量

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)])]), Author(id=1329458070972904122, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071044207292, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070972904122, language=EN, stringName=Haodong Chen, firstName=Haodong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108, bio={"content":"

born in 2000. Master candidate. His main research interests include programmable networks and datacenter congestion control

"}, bioImg=null, bioContent=

born in 2000. Master candidate. His main research interests include programmable networks and datacenter congestion control

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071123899069, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458070972904122, language=CN, stringName=陈浩东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1福州大学计算机与大数据学院 福州 350108, bio={"img":"kJBaz1FQvskYAkFEE0+CFQ==","content":"

2000年生. 硕士研究生. 主要研究方向为可编程网络、数据中心拥塞控制

"}, bioImg=kJBaz1FQvskYAkFEE0+CFQ==, bioContent=

2000年生. 硕士研究生. 主要研究方向为可编程网络、数据中心拥塞控制

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)])]), Author(id=1329458071178425023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071249728193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071178425023, language=EN, stringName=Jitang Niu, firstName=Jitang, middleName=null, lastName=Niu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4Polytechnic Institute of Zhejiang University, Hangzhou 310015, bio={"content":"

born in 2002. Master candidate. His main research interests include network measurement and programmable networks

"}, bioImg=null, bioContent=

born in 2002. Master candidate. His main research interests include network measurement and programmable networks

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071321031362, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071178425023, language=CN, stringName=牛继堂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4浙江大学工程师学院 杭州 310015, bio={"img":"fpd8EkW4thUa4cJuqEF8tw==","content":"

2002年生. 硕士研究生. 主要研究方向为网络测量、可编程网络

"}, bioImg=fpd8EkW4thUa4cJuqEF8tw==, bioContent=

2002年生. 硕士研究生. 主要研究方向为网络测量、可编程网络

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070410867367, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=4, ext=[AuthorCompanyExt(id=1329458070419255976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070410867367, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Polytechnic Institute of Zhejiang University, Hangzhou 310015), AuthorCompanyExt(id=1329458070427644585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070410867367, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4浙江大学工程师学院 杭州 310015)])]), Author(id=1329458071379751620, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071451054790, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071379751620, language=EN, stringName=Wenjing Liu, firstName=Wenjing, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Zhejiang Media Group, Hangzhou 310005, bio={"content":"

born in 1995. Bachelor. Her main research interests include convergence media network and network security

"}, bioImg=null, bioContent=

born in 1995. Bachelor. Her main research interests include convergence media network and network security

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071526552263, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071379751620, language=CN, stringName=刘雯靓, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3浙江广播电视集团 杭州 310005, bio={"img":"/gfh34dT05u75nA4upb7WA==","content":"

1995年生. 学士. 主要研究方向为融合媒体网络、网络安全

"}, bioImg=/gfh34dT05u75nA4upb7WA==, bioContent=

1995年生. 学士. 主要研究方向为融合媒体网络、网络安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070318592676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=3, ext=[AuthorCompanyExt(id=1329458070326981285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070318592676, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Zhejiang Media Group, Hangzhou 310005), AuthorCompanyExt(id=1329458070335369894, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070318592676, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3浙江广播电视集团 杭州 310005)])]), Author(id=1329458071602049738, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458071694324428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071602049738, language=EN, stringName=Shengrui Lin, firstName=Shengrui, middleName=null, lastName=Lin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108, bio={"content":"

born in 1997. PhD candidate. His main research interests include programmable networks and in-network intelligence

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include programmable networks and in-network intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458071769821901, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071602049738, language=CN, stringName=林声睿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1福州大学计算机与大数据学院 福州 350108, bio={"img":"5QH1kmAdmEm80VS/+zH3Fg==","content":"

1997年生. 博士研究生. 主要研究方向为可编程网络、网内智能

"}, bioImg=5QH1kmAdmEm80VS/+zH3Fg==, bioContent=

1997年生. 博士研究生. 主要研究方向为可编程网络、网内智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)])]), Author(id=1329458071836930767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangdong@fzu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329458072050840274, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071836930767, language=EN, stringName=Dong Zhang, firstName=Dong, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 5, *, address=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108
5Quan Cheng Laboratory, Jinan 250103, bio={"content":"

born in 1981. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software defined networking, network virtualization and Internet QoS

"}, bioImg=null, bioContent=

born in 1981. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software defined networking, network virtualization and Internet QoS

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458072176669395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458071836930767, language=CN, stringName=张栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 5, *, address=1福州大学计算机与大数据学院 福州 350108
5泉城实验室 济南 250103, bio={"img":"LYMChngqkUFUDkxjwQYBxQ==","content":"

1981年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为软件定义网络、网络虚拟化、网络服务质量

"}, bioImg=LYMChngqkUFUDkxjwQYBxQ==, bioContent=

1981年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为软件定义网络、网络虚拟化、网络服务质量

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070138237598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=1, ext=[AuthorCompanyExt(id=1329458070146626207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Computer and Data Science, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1329458070155014816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070138237598, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1福州大学计算机与大数据学院 福州 350108)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])]), Author(id=1329458072319275734, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458072508019418, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458072319275734, language=EN, stringName=Chunming Wu, firstName=Chunming, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 5, address=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013
5Quan Cheng Laboratory, Jinan 250103, bio={"content":"

born in 1967. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network architecture, Cyberspace Endogenous Safety and Security

"}, bioImg=null, bioContent=

born in 1967. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network architecture, Cyberspace Endogenous Safety and Security

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458072621265628, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, authorId=1329458072319275734, language=CN, stringName=吴春明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 5, address=2浙江大学计算机科学与技术学院 杭州 310013
5泉城实验室 济南 250103, bio={"img":"nwtaBtUoI99JKCabnL5b0g==","content":"

1967 年生. 博士,教授,博士生导师,CCF 会员. 主要研究方向为网络体系结构、网络空间内生安全

"}, bioImg=nwtaBtUoI99JKCabnL5b0g==, bioContent=

1967 年生. 博士,教授,博士生导师,CCF 会员. 主要研究方向为网络体系结构、网络空间内生安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458070230512289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=2, ext=[AuthorCompanyExt(id=1329458070243095202, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013), AuthorCompanyExt(id=1329458070251483811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070230512289, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江大学计算机科学与技术学院 杭州 310013)]), AuthorCompany(id=1329458070486364842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, xref=5, ext=[AuthorCompanyExt(id=1329458070490559147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Quan Cheng Laboratory, Jinan 250103), AuthorCompanyExt(id=1329458070494753452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458066220757618, companyId=1329458070486364842, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5泉城实验室 济南 250103)])])]
朱龙隆1, 2, 5 , 陈翔2, 陈浩东1, 牛继堂4, 刘雯靓3, 林声睿1, 张栋1, 5, * , 吴春明2, 5
作者信息
  • 1福州大学计算机与大数据学院 福州 350108
  • 2浙江大学计算机科学与技术学院 杭州 310013
  • 3浙江广播电视集团 杭州 310005
  • 4浙江大学工程师学院 杭州 310015
  • 5泉城实验室 济南 250103
通讯作者:
作者简介:

2000年生. 硕士研究生. 主要研究方向为网络测量、可编程网络、包分类

1997年生. 博士研究生. 主要研究方向为可编程网络、网络测量

2000年生. 硕士研究生. 主要研究方向为可编程网络、数据中心拥塞控制

2002年生. 硕士研究生. 主要研究方向为网络测量、可编程网络

1995年生. 学士. 主要研究方向为融合媒体网络、网络安全

1997年生. 博士研究生. 主要研究方向为可编程网络、网内智能

1981年生. 博士,教授,博士生导师. CCF会员. 主要研究方向为软件定义网络、网络虚拟化、网络服务质量

1967 年生. 博士,教授,博士生导师,CCF 会员. 主要研究方向为网络体系结构、网络空间内生安全

An Accurate Blockchain Anomaly Detection Mechanism Built on Approximate Sketch Algorithms
Longlong Zhu1, 2, 5 , Xiang Chen2, Haodong Chen1, Jitang Niu4, Wenjing Liu3, Shengrui Lin1, Dong Zhang1, 5, * , Chunming Wu2, 5
Affiliations
  • 1College of Computer and Data Science, Fuzhou University, Fuzhou 350108
  • 2College of Computer Science and Technology, Zhejiang University, Hangzhou 310013
  • 3Zhejiang Media Group, Hangzhou 310005
  • 4Polytechnic Institute of Zhejiang University, Hangzhou 310015
  • 5Quan Cheng Laboratory, Jinan 250103
  • born in 2000. Master candidate. His main research interests include network measurement, programmable networks, and packet classification

    born in 1997. PhD candidate. His main research interests include programmable networks and network measurement

    born in 2000. Master candidate. His main research interests include programmable networks and datacenter congestion control

    born in 2002. Master candidate. His main research interests include network measurement and programmable networks

    born in 1995. Bachelor. Her main research interests include convergence media network and network security

    born in 1997. PhD candidate. His main research interests include programmable networks and in-network intelligence

    born in 1981. PhD, professor, PhD supervisor. Member of CCF. His main research interests include software defined networking, network virtualization and Internet QoS

    born in 1967. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network architecture, Cyberspace Endogenous Safety and Security

出版时间: 2024-10-01 doi: 10.7544/issn1000-1239.202440477
文章导航
收藏切换

区块链存在网络动态性强和其管理困难等问题,使得区块链普遍存在DDoS 攻击和账户接管等异常现象. 现有区块链异常检测方法多从所有区块链账户中提取历史交易信息和交易频率等特征加以分析以甄别异常. 然而,随着区块链数据规模的不断扩大,现有方法在提取特征时面临内存消耗高、检测精度低的挑战. 为此,提出了一种高检测精度、低内存开销的区块链异常检测机制,该机制采用近似测量算法将区块链异常检测转化为异常交易账户检测,包括区块内异常账户和跨区块异常账户. 对于区块内异常账户,即仅存在于单个区块内的异常账户,使用Sketch算法进行账户识别,精度高. 而对于存在于多个区块且难以通过单个区块信息检测到的跨区块异常账户,则通过聚合和分析多区块信息进行账户的准确检测. 使用包含88 847个区块的真实区块链数据评估上述机制. 实验结果表明,与现有代表性方法对比,所提出的机制将区块链异常检测的召回率最高提升了6.3倍,F1分数最高提升了4.4倍. 因此,提出的高精度区块链异常检测机制对于规范区块链交易行为、维护系统安全性具有意义.

区块链  /  安全  /  异常检测  /  近似算法  /  Sketch

Blockchain suffers from network dynamics and management difficulties, making the anomalies such as DDoS attacks and account takeovers possible. Existing approaches that detect anomalies in blockchains extract features, such as historical transaction information and transaction frequencies, from blockchain accounts to identify anomalies. However, the increasing scale of blockchain data results in the challenge of high memory consumption and low detection accuracy in the feature extraction of existing approaches. To address this challenge, we propose a blockchain anomaly detection mechanism that achieves detection accuracy and reduces resource footprints. This mechanism embraces approximate sketching algorithms to transform the detection of blockchain anomalies into that of malicious accounts, including intra-block accounts and inter-block accounts. For intra-block accounts, i.e., the malicious accounts that occur inside a single block and the mechanism uses sketching algorithms to collectively filter out those accounts with high precision. For inter-block accounts, malicious accounts can be hardly detected by analyzing the information of a single block, it aggregates multi-block information to accurately detect those accounts. We evaluate our mechanism with real Ethereum block data comprising of 88847 blocks. Our results indicate that compared with typical existing approaches, our mechanism improves the recall of detecting blockchain anomalies by up to 6.3 times and the F1 score by up to 4.4 times. Therefore, our proposed blockchain anomaly detection mechanism can bring benefits to regulating blockchain transaction behaviors and maintain system security.

blockchain  /  security  /  anomaly detection  /  approximate algorithms  /  Sketch
朱龙隆, 陈翔, 陈浩东, 牛继堂, 刘雯靓, 林声睿, 张栋, 吴春明. 基于近似测量算法Sketch的高精度区块链异常检测机制. 计算机研究与发展, 2024 , 61 (10) : 2526 -2539 . DOI: 10.7544/issn1000-1239.202440477
Longlong Zhu, Xiang Chen, Haodong Chen, Jitang Niu, Wenjing Liu, Shengrui Lin, Dong Zhang, Chunming Wu. An Accurate Blockchain Anomaly Detection Mechanism Built on Approximate Sketch Algorithms[J]. Journal of Computer Research and Development, 2024 , 61 (10) : 2526 -2539 . DOI: 10.7544/issn1000-1239.202440477
区块链是一种去中心化的新型分布式计算技术,其结构是由多个数据块(又名区块)组合成的链,每个区块都包含前一个区块的加密哈希、时间戳、事务列表和其他字段. 目前,区块链技术已被广泛应用于比特币、以太坊等加密货币的交易记录[1-2],然而在网络层面临的安全问题日益严峻. 由于区块链网络流量动态性强、管理难度大,区块链易遭受由异常交易账户发起的网络层攻击[3-4],如DDoS攻击,为避免区块链被攻击后导致的重大经济损失,区块链异常检测被普遍认为是一个亟待解决的前沿科学问题[5-7].
现有区块链网络层异常检测方法主要分为静态规则检测方法和采样检测方法两类[8-9]. 一方面,静态规则检测方法指的是通过提取静态的区块链交易特征,形成安全规则,从而检测异常交易账户的方法[10-11],它们通过提取当前账户的交易历史信息、交易金额、交易频率和操作码等特征,对比当前账户与正常账户特征的统计信息,从而验证当前账户行为是否正常. 然而,如表1所示,随着区块链上交易数据规模的增加,静态规则检测方法的内存开销急剧增加,难以保证低内存开销. 另一方面,采样检测方法[12-15]从区块链交易数据中按照一定的采样率提取部分区块链账户特征以推断异常账户. 然而该方法依赖于采样,难以保证高检测精度.
为解决上述现有方案存在的问题,本文提出了一种高检测精度、低内存开销的区块链异常检测机制. 本文的核心贡献主要包括3个方面:
1)通过分析常见区块链异常,包括DDoS攻击、欺诈、账户接管、非法活动等,从而将区块链异常检测问题转化为异常交易账户检测问题,这些异常账户存在高交易额、高交易频率、高交易对象数量的特征.
2)提出了一种基于近似测量算法Sketch的高精度区块链异常检测机制. Sketch是一种用于信息统计的数据结构,以较小的内存开销保留海量数据中的关键信息,并支持快速的信息查询. 该机制包含2个检测阶段:在第1阶段,通过Sketch过滤得到高交易额、高交易频率、高交易对象数量的区块内异常账户. 在第2阶段,基于第1阶段的分析结果,以多个区块为一个检测窗口,聚合多区块交易信息,以准确检测跨区块异常账户(即存在多个区块且难以通过单个区块信息检测异常账户).
3)基于包含88 847个区块的真实以太坊区块链数据评估了提出的区块链异常检测机制. 实验结果表明,与现有方法相比,本文提出的机制将区块链异常检测的召回率最高提升了6.3倍,F1分数最高提升了4.4倍. 同时基于真实DDoS攻击数据集,验证了本文机制在DDoS攻击场景下的有效性,召回率达到99%,达到理论最优精度.
本节介绍常见区块链异常类型.
1)DDoS攻击. DDoS攻击是指运用大量计算机同时向受害者主机请求服务,占满受害者主机资源导致其拒绝为正常主机提供服务[16],在区块链网络中,DDoS攻击表现为交易金额和交易次数的突然上升[17] .
2)欺诈. 欺诈者以诱人的远期收益为诱饵,来骗取投资者的投资,主要表现为庞氏骗局[18]. 在庞氏骗局中,欺诈者向初期投资者许诺短期内的投资能得到高回报,随后用新投资人的资金作为初期投资者的收益,以吸引更多的投资者. 在区块链中表现为一个账户拥有较多的资金流入,但只有很少的资金流出[19].
3)账户接管. 攻击者通过恶意软件或网络钓鱼的方式非法获取受害者设备或账户的权限,从而接管受害者账户以偷取资金[20]. 近年的市场分析报告指出2024年已有价值1693万美元的加密货币被盗,数额是2023年的2倍. 在区块链中表现为一个非活跃账户短期内发生较大金额的资金流出.
4)非法活动. 由于区块链的匿名特性,数字货币也被用于洗钱等非法活动[21]. 在区块链中表现为一个活跃账户长期拥有高额的资金流入或流出[22].
本节介绍现有区块链异常检测方法,主要包含静态规则检测方法和采样检测方法.
静态规则检测方法主要通过提取以太坊钱包交易的特征进行异常检测. 现有研究表明,人为操作的以太坊钱包连续交易的时间差呈现幂次分布律[23],因此Zwang等人[10]利用以太坊钱包连续交易之间的时间差分布来识别周期性和不规则的异常;Chen等人[11]通过从交易中提取账户特征(如余额和支付率等)、操作码特征和交易频率等信息来识别庞氏骗局. 然而,随着攻击类型和手段的不断演变,静态规则检测方法中静态、单一的防御规则无法应对攻击变化[24]. 此外,随着区块链数据规模增大,内存开销也急剧上升.
采样检测方法从大量数据中按一定采样率提取所需特征,常被用于大流量数据的特征提取与分析[12-15]. 采样检测方法从区块链交易数据中按照一定的采样率提取数据子集,减少数据采集和分析成本. 通过分析数据子集中异常账户的特征,检测方法进而推断区块链交易中的异常交易账户. NetFlow[13]改变采样率来权衡精度与内存. OpenSample[15]将 sFlow[12]的采样功能集成到控制器中以提升精度. 然而,采样检测方法依赖于采样率的设定,随着区块链上数据规模的增加,无法同时兼顾高检测精度和低内存开销.
本节将详细介绍基于近似测量算法Sketch的高精度区块链异常检测机制. 首先定义本文的异常检测任务;其次提出基于Sketch的区块链异常检测机制以及关键算法;最后介绍检测机制的实现. 表2总结了本文主要符号的含义.
本文分析区块链网络常见攻击,如DDoS攻击、欺诈、账户接管、非法活动等. 其核心特征为:在一段时间内,单个或多个账户进行了大量交易,拥有较高的资金流入或流出.
因此,本文专注于区块链交易中的异常账户的检测,其主要特征包括高交易额、高交易频率、高交易对象数量. 具体为:
1)高交易额或高交易频率的异常账户. 在一段时间内,考虑一个区块链网络内的总交易额或总交易次数. 如果某个区块链账户所涉及交易的总额或交易次数占区块总交易总额或总次数的主要部分,可认定为异常交易账户.
形式上,设定阈值$ T $,将账户$ {C} $的交易额、交易次数分别记为$ V alueC $、$ CountC $,总交易额记为$ T otalV alue $,总交易次数记为$ T otalCount $. 异常交易账户判定条件为:
$ ValueC\ge T\times T otalV alue \text{,} $
$ CountC\ge T\times T otalCount . $
2)高交易对象数量的异常账户. 在一段时间内,考虑一个区块链网络内各个账户的出度,即与其发生交易的不同账户的数量. 如果某个区块链账户的出度或入度超过设定的阈值,可认定为异常账户.
形式上,设定阈值为θ,账户$ C $的出度或入度记为$ DegC $. 异常账户判定条件为:
$ DegC\ge \theta . $
Sketch作为经典的概率统计算法,支持对大规模数据的统计与查询,同时减少存储数据特征所需的空间[25]. Sketch近似测量的原理是利用亚线性的摘要数据结构实现大规模数据的聚合、采样或压缩. 对于输入的数据流,Sketch首先解析并获取数据包的信息,如源IP地址和目的IP地址;其次,利用哈希函数找到其在摘要数据结构中对应的计数器;再次,根据数据包值更新计数器统计值;最后,在一个测量周期结束时,遍历摘要数据结构获取最终统计值. 由于将属于相同流的数据映射到同一个计数器中,Sketch大幅度降低了内存资源开销. 但由于流之间存在哈希碰撞,即多条流映射到同一个计数器中,导致Sketch得到的统计值存在一定误差. 以频率估计为例,假设在1个测量周期内,流A包含1个数据包,流B包含9个数据包,且流A与流B发生哈希碰撞. 当数据包传入时,首先,解析数据包获取键信息;其次,利用哈希函数定位计数器位置;再次,将计数器值累加1;最后,查询计数器得到统计值为10. 因此,对于占主导地位的大象流,Sketch以较低的内存开销取得了较高的测量精度. Sketch已被广泛用于实现大流检测[25]、熵估计[26]等应用. 在区块链中,Sketch主要应用于区块摘要[27]、支付验证[28]、唯一地址检查[29-30]等,实现存储空间和查询精度之间的平衡. Rottenstreich[31]提出使用Sketch生成多个连续区块的摘要. 相较于使用布隆过滤器的简易摘要,基于Sketch的区块摘要在维持较小存储开销的同时可提供更多交易信息.
Sketch为解决已有区块链异常检测方法的高内存、低准确度挑战提供可行思路. HashPipe[32]是一种广泛应用于识别网络数据流中大象流的Sketch算法,通过多级哈希表的流水线机制在有限内存中准确跟踪大流量数据. HyperLogLog[33]是一种典型的用于估计大规模数据集合基数(即不同元素数量)的Sketch算法,通过概率算法和哈希函数在有限内存中提供高准确度的基数估计.
本文所提基于Sketch的区块链异常检测机制如图1所示,包括2个检测阶段:基于HashPipe与HyperLogLog的区块内检测和跨区块检测.
在第1个阶段,为检测高交易额或高交易频率的异常账户,在每个区块内,本文利用HashPipe近似维护Top-K交易额或交易频率的账户. 在每个检测周期开始时,创建包含若干计数器、大小固定的HashPipe数据结构. 针对每条新发起的交易,提取其发送方或接收方的账户信息、交易金额信息插入计数器. 在每个检测周期结束时,对比设定的阈值,判断每个计数器中的账户是否为区块内异常账户. 然而,难以检测存在于多个区块且难以通过单个区块信息检测到的异常账户. 对此,在第2个检测阶段,本文利用多区块信息. 为避免第1阶段的影响,可选择剔除已判定为异常的账户. 在一个检测周期内,同时考虑多个区块的交易信息检测跨区块异常账户. 最后,聚合区块内检测、多区块联合检测两阶段得到异常账户.
为检测高交易对象数的异常账户,在每个区块内,本文利用HyperLogLog近似维护Top-K交易账户数的账户. 对于每个检测周期,创建K个包含$ m $个桶的HyperLogLog数据结构,维护K个账户的交易对象数量.
对于每条新发起的区块链交易,提取其发送方、接收方信息,插入HyperLogLog. 检测周期结束时,基于每个HyperLogLog内维护的交易对象数量判断其对应账户是否为异常. 同样地,跨区块异常账户难以通过单个区块信息检测. 因此一方面,本文在一个检测周期内处理多个区块的交易信息,得到异常账户候选;另一方面,本文维护了一个全局的HyperLogLog结构,聚合多个检测周期内得到的异常账户候选的信息. 最后一个检测周期结束后,本文在全局HyperLogLog结构中得到异常账户.
本文将区块链账户分类为异常账户与正常账户. 为衡量检测的性能,本文与遍历完整区块数据集计算得到的准确异常账户分类结果比较,基于对比结果计算真阳性TP、假阳性FP、真阴性TN、假阴性FN. 在此基础上,计算精度(precision)、召回率(recall)、F1分数为:
$ {精}{度}=\dfrac{{T}{P}}{{T}{P}+{F}{P}}\times 100\%\text{,} $
$ {召}{回}{率}=\dfrac{{T}{P}}{{T}{P}+{F}{N}}\times 100\%\text{,} $
$ {F}1{分}{数}=2\times \dfrac{{精}{度}\times {召}{回}{率}}{{精}{度}+{召}{回}{率}}. $
本文的目标是检测在一段时间内具备高交易额、高交易频率的账户. 遍历区块链记录,所有账户交易记录的方法精度和召回率高. 然而,面对大规模区块数据,存储开销高. 对此,本文通过一种基于多层流水线机制的Sketch应对这个问题,即HashPipe. 然而,跨区块异常账户存在于多个区块且难以通过单个区块信息检测. 因此,本文提出一种两阶段检测的算法. 第1阶段基于HashPipe检测区块内异常交易账户;第2阶段同时考虑多个区块,挖掘在单个区块内不占主导地位的跨区块异常账户. 聚合两阶段异常账户.
1)第1个检测阶段. HashPipe的核心思想是构建流水线结构的多层Sketch,包括更新、查询2个关键操作. 如图2所示,HashPipe由多个一维Sketch组成,交易信息传入后可能经过多层Sketch.
如算法1所示,首先通过预设的哈希函数计算区块链账号Acc在当前层Sketch的桶位置L. 如果该位置已被占用,本文根据账号的交易额或者交易次数决定是否以新账号替换原区块链账号信息. 若替换,则将原账号及其交易额或交易次数信息推送至下一层Sketch,重复上述操作. 若某个账号被踢出最后一层Sketch,则丢弃. 因此,本文可以近似维护当前区块交易金额或交易频率最高的K个账户信息.
算法1. HashPipe更新算法.
输入:交易信息(账户Acc,交易金额value),HashPipe数据结构h,多个哈希函数HF;
输出:更新后的HashPipe数据结构h.
① for i←0 to d–1 do
②  L←HF_i (Acc);
③ if h[i][L].key==Acc then
④   h[i][L].v += value;/*若统计频率则加1*/
⑤  return;
⑥ end if
⑦ if h[i][L].key == null then
⑧  (h[i][L].key, h[i][L].v) ← (Acc, value);
⑨  return;
⑩ end if
⑪ if h[i][L].key≠null&&h[i][L].v < value then
⑫   swap (h[i][L].key, Acc);
⑬   swap (h[i][L].v, value);
⑭ end if
⑮ end for
⑯ return h.
检测周期结束后,通过遍历HashPipe数据结构,本文得到统计值高于异常阈值T×TotalValue或T×TotalCount的异常账户. 具体过程如算法2所示.
算法2. HashPipe异常账户搜索算法.
输入:阈值T,HashPipe数据结构h,检测周期总交易额TotalValue;
输出:异常账户集合List.
① List←empty;
② H←T×TotalValue; /*以交易额为例,若统计交 易次数则为T×TotalCount*/
③ for i ← 0 to d–1 do
④ for key in h[i] do
⑤  if key.value > H then
⑥    List.append (key);
⑦  end if
⑧ end for
⑨ end for
⑩ return List.
2)第2个检测阶段. 如算法3所示,以高交易额账户检测为例,本文首先联合n个区块的交易数据,然后构建一个大小为d×m′的HashPipe数据结构用于交易额统计. 对于每一条交易数据(Acc, value),本文可以选择判断其账户Acc是否在第1轮检测中已被判定为异常. 若是,则不插入数据结构中,从而剔除单区块中高交易额账户的影响;否则,利用算法1将Acc插入HashPipe. 检测周期结束后,本文利用算法2搜索异常账户. 最后,将2个阶段的检测结果聚合,得到最终的异常账户列表. 类似地,对于检测一段时间内前K个最高交易频率的账户,将算法3稍作修改即可,本文不再详细描述其过程.
算法3. 多区块聚合的异常检测算法.
输入:阈值T,检测周期总交易额TotalValue,n个区块的交易数据Trans[1],…,Trans[n],HashPipe结构的层数d和每层的计数器数m;
输出:异常账户集合List.
① for i←1 to n do
②  TransTotal.append (Trans[i]);
③ end for
④ H←T×TotalValue; /*以交易额为例,若统计 交易次数则为T×TotalCount*/
⑤ Construct (h, d, m′); /*构建大小为d×m′的 HashPipe数据结构h*/
⑥ for (Acc, value) in TransTotal do
⑦  Insert (Acc, value, h);
⑧ end for
⑨ List←Query (h, H); /*遍历h,搜索交易金额 高于H的异常账户*/
⑩ return List.
对于高交易额或高交易频率的异常账户检测问题,第1个检测阶段,本文在HashPipe中维护$ k $个计数器,其中$ k=d\times m $,d和m分别表示HashPipe结构的层数和每层的计数器数. 每个计数器维护一个二元组(账户信息,账户交易总额或账户交易总次数). 本文使用5个字节存储账户信息的前40位信息,4个字节存储账户交易总额或总次数. 尽管未存储完整账户信息,但在一段时间内2个前40位信息完全一致的账户都是异常交易账户的概率可以忽略不计. 第2个检测阶段,类似地,本文对于$ n $个区块维护一个大小为$ d\times m' $的HashPipe数据结构,其中,$m' $表示多区块检测时构建的HashPipe结构每层的计数器数. 综上,对于单个区块而言,本文的内存开销为$ 9\times k\times (1+m'/n) $字节. 特别地,在本文捕获的真实以太坊区块链数据集中,一个区块完整交易数据的平均大小约为22 KB,当$ k $=10,$ m' $和$ n $=50时,所提检测方法的内存仅为区块完整交易数据大小的0.8%.
本文的目标是检测在一段时间内发生交易的对象数量高的异常账户,即节点度高的账户. 由于出度、入度的估计方法一致,以出度高的异常账户检测为例.
本文利用HyperLogLog近似维护出度最高的$ k $个账户信息及其出度. HyperLogLog由$ m $个计数器桶构成,核心思想是使用多个哈希函数将区块交易信息(统计出度,本文取发送方账户信息)映射到多个桶内,在计数器桶中记录首次出现1的位置,即连续前导0的数量. 利用$ m $个计数器桶内的统计数据,使用调和平均值估计账户的出度. 考虑到每个区块内交易记录有限,异常账户在单个区块中可能不占主体地位. 因此,如图3所示,本文在1个检测周期内同时处理多个区块的交易信息. 此外,本文额外维护全局HyperLogLog结构,聚合多个检测周期得到的异常账户信息以实现更准确的高出度的异常账户检测,也便于在区块链网络中在线统计和离线检测.
具体如算法4所示,本文在每个检测周期内同时考虑$ n $个区块的交易信息,创建$ k $个大小为$ m $的HyperLogLog数据结构. 首先遍历所有交易账户信息,包含发送方Acc.from和接收方Acc.to. 对于已与某个发送方Acc.from对应的HyperLogLog结构进行更新操作. 具体而言,对接收方Acc.to信息进行哈希操作,提取哈希值的前b位作为桶索引,提取剩余位计算前导0的数量,并与当前HLL[i]中维护的出度值比较,更新HLL[i]. 对于未被保留的发送方Acc.from,若创建的k个HpyerLogLog有未被使用者,则加入;否则,依据出度值大小进行$ k $个HyperLogLog所维护发送方信息的替换. 每个检测周期结束后,计算各HyperLogLog中的调和平均值,估计出度,将其中高于阈值$ \theta $的发送方及其出度估计值合并至全局数据结构,更新全局异常账户集合List. 最后,检测交易对象数量多的异常账户.
算法4. 高交易对象数量的异常账户检测算法.
输入:阈值θ,HyperLogLog数量k及其的桶计数器数m, n个区块的交易数据Trans[1],…,Trans[n];
输出:更新后的全局异常账户集合List.
/*对于每个检测周期*/
① Init (TransTotal, Trans);
② HLL = HLLConstruct (k, m);
③ for Acc in TransTotal do /*遍历所有账户*/
④ for i = 1 to k do /*遍历k个数据结构*/
⑤  if Acc.from == HLL[i]. key then
⑥    Update (HLL[i], Acc);/*更新HLL*/
⑦  end if
⑧  if HLL[i] == null then
⑨    Insert (HLL[i], Acc);/*插入HLL*/
⑩  end if
⑪  if HLL[i] ≠ null && Esti (HLL[i])==1 then    /*若出度为1替换为新账户相关   信息*/
⑫    swap (HLL[i], Acc);
⑬  end if
⑭ end for
⑮ end for
⑯ ListCurrenct←Query (HLL, θ);/*遍历k个HLL, 计算调和平均,估计出度,返回出度估计 值高于θ 的异常账户*/
⑰ Merge (List, ListCurrent);/*合并到全局的 HyperLogLog,更新全局异常账户集合List*/
⑱ return List.
对于账户出度估计问题,本文在HyperLogLog中维护$ m $个桶,即$ m $个大小为1字节的计数器. 同样地,使用5个字节存储账户信息的前40位信息. 因此,对于每个需要估计出度的账户,本文的内存开销为$ m+5 $字节,当$ k $=14,$ m $=5时,仅占单个区块平均大小的0.6%.
定理1. 对于高交易对象数量的异常账户检测,以账户出度估计为例,本文在HyperLogLog中维护$ m $个桶,每个需要估计出度账户的出度估计值的相对误差标准差约为$ \dfrac{1.04}{\sqrt{m}} $.
证明. 假定某个需要估计出度的账户,其不同交易对象的数量为n,使用m个桶记录最大前导0的数量,分别为M[i]. 根据泊松分布可知,估计值期望$ {E}= {\alpha }_{m}{m^{2}}{\left(\displaystyle\sum_{i=1}^{m}{2}^{-M\left[i\right]}\right)}^{-1} $,其中,校正常数${\alpha }_{m}= $$ \left(m{\displaystyle\int }_{0}^{\infty } \times {\left({\rm{lb}}\left(\dfrac{2+t}{t}\right)\right)}^{m}{\rm d}t\right)^{-1} $. 为分析$ {E} $的方差,取$ {{Z}}_{i}= $${2}^{-M\left[i\right]} $,其期望值$ {{E}[{Z}}_{i}]=\dfrac{m}{2n} $,方差$ {{V}[{Z}}_{i}] $$ ={E}[{{{Z}}_{i}^{2}}] -$$ {\left({{E}[{Z}}_{i}\right])^{2}} $,展开计算得到$ {{V}[{Z}}_{i}]\approx \dfrac{m}{4n} $. 由于$ {E} $涉及m个桶,聚合m个独立同分布的$ {{Z}}_{i} $的期望和方差,得$ {E}\left[\displaystyle\sum_{i=1}^{m}{{Z}}_{i}\right]=\dfrac{{m^{2}}}{2n} $,$ {V}\left[\displaystyle\sum_{i=1}^{m}{{Z}}_{i}\right]=\dfrac{{m^{2}}}{4n} $. 根据中心极限定理,标准差${\sigma }_{{\displaystyle\Sigma}{{Z}}_{i}}= $$ \sqrt{{V}\left[\displaystyle\sum_{i=1}^{m}{{Z}}_{i}\right]}=\dfrac{m}{2\sqrt{n}} $. 估计值$ {E} $是基于$ \displaystyle\sum_{i=1}^{m}{{Z}}_{i} $的反比值,即$ {E}={\alpha }_{m}\dfrac{{m^{2}}}{\displaystyle\sum_{i=1}^{m}{{Z}}_{i}} $,则$ {E} $的标准差$ {\sigma }_{{E}}\approx {\alpha }_{m}\dfrac{{m^{2}}{\sigma }_{{{Z}}_{i}}}{{\left({E}\left[\displaystyle\sum_{i=1}^{m}{{Z}}_{i}\right]\right)^{2}}}= $${\alpha }_{m}\dfrac{2n}{m} $. 因此,$ {E} $的相对误差$ \dfrac{{\sigma }_{{E}}}{{E}\left[{E}\right]}\approx \dfrac{4{n^{2}}}{{m}^{3}} $. 结合实验经验和理论计算,校正常数$ {\alpha }_{m} $通常选为$ {\alpha }_{m}=\dfrac{0.721\;3}{1+1.079/m}\approx $$0.721\;3 $. 所以,最终的相对误差标准差$ \mathrm{\sigma }\left(\dfrac{\hat{n}}{n}\right)\approx \dfrac{0.721\;3\sqrt{m}}{\sqrt{8}n}=\dfrac{1.04}{\sqrt{m}} $. 因此,账户出度估计值的相对误差标准差约为$ \dfrac{1.04}{\sqrt{m}}. $ 证毕.
为实现所提异常账户检测机制,本文为发送方或接收方维护2个HashPipe结构用于统计交易金额和交易频率,维护多个HyperLogLog结构用于估计账户出度或入度信息.
1)统计阶段. 利用构建的大小固定的HashPipe数据结构存储多个区块中交易信息,包括发送方或接收方账户、交易金额. 利用多个大小固定的HyperLogLog数据结构进行账户出度或入度估计. 周期性发送统计数据.
2)处理阶段. 针对每个检测周期的统计数据,基于所提方法检测高交易金额、高交易频率、高交易对象数量的异常账户. 此外,可对比2个周期的检测结果以支持对交易金额、交易频率急剧变化账户的检测. 最后,由区块链网络管理员处理上报的异常账户.
当区块链数据不断增加时,本文执行以下步骤:首先,提取新交易记录中的部分信息. 以高交易金额异常账户检测为例,可提取新交易记录中的发送方信息、交易金额信息. 然后,利用更新操作将二元组(发送方,交易金额)记录到本文机制所构建的HashPipe,HyperLogLog数据结构中. 最后,在每个检测周期结束时,提取统计数据,清空2种数据结构已存储的信息以便于下一周期的检测,离线分析当前周期或结合以往多个周期的数据得到异常账户候选列表.
1)数据集捕获. 本文采集了真实以太坊区块链交易信息[34]. 数据集包含88847个真实区块,每个区块平均包含约98条交易信息,大小约为22 KB. 数据集总大小为1908 MB,交易总次数为8705166,包含1546258个不同的发送方以及1453510个不同接收方.
2)对比算法. 本文构造2类对比算法:针对异常账户的静态规则检测算法、采样检测方法.
① 静态规则检测算法. 由于现有静态规则检测方法往往针对特定攻击而非本文所提异常账户的检测,本文构造如下静态规则检测算法:使用交易账户信息、交易金额为特征,检测规则为本文所提出的判定为异常的条件. 现有静态规则检测算法[10-11]往往提取多个特征,内存开销显著高于所构造的静态规则检测算法.
② 采样检测方法. 本文采用NetFlow方法[13]对区块链数据进行采样,设置采样率γ为$ {1}/{4} $ ~ $ {1}/{128} $.
以发送方为例,本文分析了区块链数据集中账户交易额、交易频率、出度的情况. 如表3~5所示,一方面,大多数账户的交易额低于1 ETH,占账户总数的75.7689%;超过半数账户交易次数仅为1,交易次数超过100的账户占比不超过1%;超过70%的账户出度仅为1,出度超过10的账户占比小于1%. 另一方面,账户的平均交易额、交易频率、出度分别为9.86142 ETH、5.62983次、2.17878个. 综上所述,区块链中大多数账户的交易额、交易频率、交易对象数较低,易存在跨区块异常账户.
本文检测交易额高的区块内、跨区块异常账户,以及评估了仅执行第1个检测阶段时在不同阈值、内存开销条件下的召回率. 表6展示了平均召回率变化情况. 随着阈值T的增加以及被判定为异常的帐户数量降低,在相同内存条件下,召回率得到提升. 此外,随着HashPipe内存开销的增加,本文可以维护更多异常账户候选,召回率增加. 在表6内所有配置下,本文提出检测机制的检测平均精度均为100%.
然而,对于高交易频率的区块内异常账户检测,召回率较低. 如表7所示,在相同的内存和阈值条件下,$ d =14$、$ m=1 $、阈值T=10–2,高交易频率异常账户检测平均召回率为60%,远低于高交易额异常账户检测的平均召回率(100%). 对此,注意到高交易频率问题中的异常账户往往是跨区块异常账户. 本文执行第1个、第2个检测阶段. 在第2个检测阶段中,1个检测周期包含50个区块的信息. 表8展示了50个区块下高交易频率异常账户检测的平均召回率,由于跨区块异常账户占主体地位,以$ m' $=50,$ d $=14且阈值T=10–2为例,平均召回率从60%提升至100%. 随着内存大小的增加,平均召回率也得到提升. 同样地,表8中所有参数配置对应的检测平均精度均为100%.
综上所述,本文提出的检测机制对于高交易额异常账户检测任务,在有限内存下实现较高召回率. 对于高交易频率异常账户检测,单区块内检测的性能低,本文检测跨区块异常账户,相同阈值下召回率最高提升了4.3倍.
对于账户交易对象数量(本文取出度),使用基于HyperLogLog的算法. 对于每个区块,维护最多7个HyperLogLog数据结构以存储出度最高的7个异常账户. 图4展示了检测周期不同区块数量和出度阈值$ \theta $下的平均精度和召回率. 本文取检测周期分别为1,5,20个区块,阈值$ \theta $分别为50,100,500,1000. 如图4所示,对于单个区块,当阈值$ \theta $为50,100时,平均精度均为100%. 然而其平均召回率较低,分别为37%和46%. 当检测周期中包含20个区块的信息时,其平均召回率分别提升至45%和52%. 本文同时统计了50个真实区块,而HyperLogLog的数量有限,当阈值$ \theta $较小时,异常账户数量多,导致平均召回率低. 而随着阈值$ \theta $增加,异常账户数量降低,平均召回率逐步提升. 本文提出的检测机制的平均召回率最高达86%.
本文改变异常账户判定标准,评估HyperLogLog的平均精度、平均召回率. 具体而言,固定检测周期为5个区块且阈值$ \theta $=500,设定阈值调整因子$ f actor $,即阈值$ f actor \times \theta $,探究异常账户判定标准对检测性能的影响. 如图5所示,随着$ f actor $的降低,平均召回率从76%提升至83%. 与此同时,平均精度从93%下降至87%. 在实际应用中,可以根据需求选择不同的factor,权衡检测的召回率与精度.
综上所述,本文提出的机制对于高交易对象数量异常账户,最高达到了100%的精度和86%的召回率;对跨区块异常账户,使用多区块信息提升召回率.
本文从真实以太坊区块链完整数据集中提取DDoS特征的攻击数据集. 数据集包含500个区块,每个区块平均包含约100次交易. 数据集总大小为10.73 MB,包含1400个不同发送方和1001个不同接收方. 其中,400个账户对同一个账户发起30~80次交易,构成对其的DDoS攻击.
对此,本文检测高交易频率的异常账户. 取检测阈值T为固定值2×10–3,检测周期包含50个区块,$ m' $均取50,改变d的取值,评估DDoS账户检测的平均召回率、平均精度. 如图6所示,本文对于DDoS数据集的平均召回率最高达到99%. 随着d值从2增加至18,高交易频率异常账户平均精度保持100%. 而由于数据集内异常账户数量较多,随着内存降低,所能维持的异常账户候选数量降低,召回率随之下降,但精度仍保持在100%. 综上所述,本文提出的机制可以在DDoS数据集下实现有效的异常账户检测,在有限内存条件下达到了99%的召回率和100%的精度.
图7和图8分别展示了多种异常检测方法在高交易额异常账户检测下的平均召回率、F1分数. 检测阈值T取10–3,一个检测周期包含50个区块的信息. 本文所提检测机制的召回率、F1分数趋近于基于静态规则的检测方法,高于采样检测方法. 召回率方面,本文检测方法召回率为99.4%,接近基于静态规则的检测方法,相较于采样检测方法的召回率(95.1%~96.3%)有所提升. F1分数方面,本文检测方法接近基于静态规则的检测方法,相较于采样检测方法的F1分数(0.975~0.981)有所提升. 而本文提出的检测机制的内存开销远小于静态规则检测方法和采样检测方法,分别最高降低了99.4%和98.1%.
图9和图10分别展示了多种异常检测方法在高交易频率异常账户检测下的平均召回率、F1分数. 检测阈值$ T $取10–3,1个检测周期包含50个区块的信息. 如图9所示,召回率方面,本文所提检测机制的平均召回率为95.1%,接近基于静态规则的检测方法,相较于采样检测方法的平均召回率,最高提升了6.3倍. F1分数方面,如图10所示,本文所提检测机制的F1分数为0.975,接近基于静态规则的检测方法,相较于采样检测方法最高提升了4.4倍. 而本文提出的检测机制的内存开销远小于静态规则检测方法和采样检测方法,F1分数分别最高降低了99.7个百分点和98.8个百分点.
图11和图12分别展示了多种异常检测方法在高交易对象数量异常账户检测下的平均召回率和F1分数. 当阈值T取1000时,本文提出的检测机制的内存开销较低,平均召回率和F1分数接近静态规则检测方法. 召回率方面,本文检测方法的内存开销较低,相比静态规则检测方法与采样检测方法(采样率γ取1/4),每个检测周期所需的内存开销减少了85.8%和96.4%,而本文达到了86%的平均召回率,接近于静态规则检测方法,优于采样检测方法在不同采样率下的平均召回率.
综上所述,相比与静态规则检测方法与采样检测方法,本文提出机制对区块链异常交易账户进行检测,使用较小的内存实现了高检测召回率和F1分数.
本文提出了一种基于近似测量算法Sketch的高精度区块链异常检测机制. 该机制面向高交易额、高交易频率、高交易对象数量的异常账户检测,构建2个检测阶段:第1阶段,通过Sketch过滤得到高交易额、高交易频率、高交易对象数量的区块内异常账户. 第2阶段,基于第1阶段的分析结果,以多个区块为1个检测窗口,聚合多区块交易信息,以准确检测跨区块异常账户. 基于包含88847个区块的真实以太坊区块链数据评估了提出的区块链异常检测机制. 实验结果表明,与现有方法相比,本文提出的机制将区块链异常检测的召回率最高提升了6.3倍,F1分数最高提升了4.4倍. 同时基于真实DDoS攻击数据集,验证了本文机制在DDoS攻击场景下的有效性,召回率达到99%,达到理论最优精度.
未来的工作包括2个方面:1)关于检测任务类型的扩展,如何利用Sketch算法支持更多异常类型的检测. 2)如何在保证精度、召回率的前提下,将检测方法部署至硬件设备,嵌入真实区块链网络环境.
作者贡献声明:朱龙隆负责核心算法设计和论文撰写;陈翔负责系统架构并参与论文撰写;陈浩东负责实验方案设计;牛继堂负责核心算法实现;刘雯靓参与算法实现;林声睿指导本文设计;张栋指导本文设计并参与论文撰写;吴春明指导本文工作开展和论文撰写. 朱龙隆和陈翔对本文的贡献相同.

参考文献 引证文献
排序方式:
1
Wood G. Ethereum: A secure decentralised generalised transaction ledger[J]. Ethereum Project Yellow Paper, 2014, 151(2014): 1−32
2
Wright C S. Bitcoin: A peer-to-peer electronic cash system[J]. SSRN Electronic Journal, 2008, 3440802: 10−2139
3
韩璇,袁勇,王飞跃. 区块链安全问题:研究现状与展望[J]. 自动化学报,2019,45(1):206−225
Han Xuan, Yuan Yong, Wang Feiyue. Security problems on blockchain: The state of the art and future trends[J]. Acta Automatica Sinica, 2019, 45(1): 206−225 (in Chinese)
4
江沛佩,王骞,陈艳姣,等. 区块链网络安全保障:攻击与防御[J]. 通信学报,2021,42(1):151−162
Jiang Peipei, Wang Qian, Chen Yanjiao, et al. Securing guarantee of the blockchain network: Attacks and countermeasures[J]. Journal on Communications, 2021, 42(1): 151−162 (in Chinese)
5
Antonopoulos A M. Mastering Bitcoin: Unlocking Ddigital Cryptocurrencies[M]. Sebastopol: O'Reilly Media, 2017
6
叶聪聪,李国强,蔡鸿明,等. 区块链的安全检测模型[J]. 软件学报,2018,29(5):1348−1359
Ye Congcong, Li Guoqiang, Cai Hongming, et al. Security detection model of blockchain[J]. Journal of Software, 2018, 29(5): 1348−1359 (in Chinese)
7
曾诗钦,霍如,黄韬,等. 区块链技术研究综述:原理、进展与应用[J]. 通信学报,2020,41(1):134−151
Zeng Shiqin, Huo Ru, Huang Tao, et al. Survey of blockchain: Principle, progress and application[J]. Journal on Communications, 2020, 41(1): 134−151 (in Chinese)
8
Hassan M U, Rehmani M H, Chen Jinjun. Anomaly detection in blockchain networks: A comprehensive survey[J]. arXiv Preprint, arXiv: 2112.06089, 2021
9
Kim J, Nakashima M, Fan W J, et al. Anomaly detection based on traffic monitoring for secure blockchain networking[C]//Proc of the 2021 IEEE Int Conf on Blockchain and Cryptocurrency (ICBC). Piscataway, NJ : IEEE , 2021: 1−9
10
Zwang M, Somin S, Pentland A S, et al. Detecting bot activity in the Ethereum blockchain network[J]. arXiv preprint, arXiv: 1810.01591, 2018
11
Chen Weili, Zheng Zibin, Ngai E, et al. Exploiting blockchain data to detect smart Ponzi schemes on ethereum[J]. IEEE Access, 2019, 7: 37575−37586
12
Case J, Fedor M, Schoffstall M, et al. A simple network management protocol (SNMP)[EB/OL]. (1990-05-02)[2024-07-13]. https://www.ietf.org/rfc/rfc1157.txt
13
Claise B. NetFlow[EB/OL]. (2004-10-02)[2024-07-13]. https://www.ietf.org/rfc/rfc3954.txt
14
Phaal P, Panchen S, McKee N. sFlow[EB/OL]. (2001-09-02)[2024-07-13]. https://www.ietf.org/rfc/rfc3176.txt
15
Suh J, Kwon T T, Dixon C, et al. OpenSample: A low-latency, sampling-based measurement platform for commodity SDN[C]//Proc of the 2014 Int Conf on Distributed Computing Systems. Piscataway, NJ: IEEE, 2014: 228−237
16
Eliyan L F, Pietro R D. DoS and DDoS attacks in software defined networks: A survey of existing solutions and research challenges[J]. Future Generation Computer Systems, 2021, 122: 149−171
17
Mirkin M, Ji Y, Pang J, et al. Bdos: Blockchain denial of service[C]//Proc of the 2020 ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2020: 601−619
18
Chen Weili, Zheng Zibin, Cui Jiahui, et al. Detecting Ponzi schemes on ethereum: Towards healthier blockchain technology[C]//Proc of the 2018 World Wide Web Conf. New York: ACM, 2018: 1409−1418
19
Andryukhin A A. Phishing attacks and preventions in blockchain based projects[C]//Proc of the 2019 Int Conf on Engineering Technologies and Computer Science. Piscataway, NJ: IEEE, 2019: 15−19
20
Chainalysis. Israeli government seizes cryptocurrency addresses associated with Hamas donation campaigns[EB/OL]. (2021-07-08)[2024-07-13]. https://blog.chainalysis.com/reports/israel-hamas-cryptocurrency-seizure-july-2021
21
Voronov T, Raz D, Rottenstreich O. A framework for anomaly detection in blockchain networks with sketches[J]. IEEE/ACM Transactions on Networking, 2024, 1(32): 686−698
22
Barabasi A L. The origin of bursts and heavy tails in human dynamics[J]. Nature, 2005, 435(7039): 207−211
23
Zhou Xuanchen, Yang Wenzhong, Tian Xiaodan. Detecting phishing accounts on Ethereum based on transaction records and EGAT[J]. Electronics, 2023, 12(4): 993
24
Voronov T, Raz D, Rottenstreich O. Scalable blockchain anomaly detection with sketches[C]//Proc of the 2021 IEEE Int Conf on Blockchain. Piscataway: IEEE, 2021: 1−10
25
Tang Lu, Huang Qun, Lee P P C. MV-Sketch: A past and compact invertible sketch for heavy flow detection in network data streams[C]//Proc of the 2019 IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2019: 2026−2034
26
Lu Jie, Zhang Zheng, Chen Hongchang, et al. Filter-Sketch: A two-layer sketch for entropy estimation in the data plane[J]. IET Communications, 2022, 16(20): 2422−2430
27
Rush T J. Enhanced adaptive Bloom filters for identifying transactions of interest in a blockchain[R/OL]. New York: QuickBlocks, 2017[2020-06-05]. http://quickblocks.io
28
Qin Kaihua, Hadass H, Gervais A, et al. Applying private information retrieval to lightweight bitcoin clients[C]//Proc of the 15th Crypto Valley Conf on Blockchain Technology (CVCBT). Piscataway, NJ: IEEE, 2019: 60−72
29
Wang Tianyu, Zhu Wenbin, Ma Qun, et al. ABACUS: Address-partitioned Bloom filter on address checking for uniqueness in IoT blockchain[C]//Proc of the 39th Int Conf on Computer-Aided Design. Virtual Event, USA: ACM 2020: 1−7
30
Shafeeq S, Zeadally S, Alam M, et al. Curbing address reuse in the IOTA distributed ledger: A cuckoo-filter-based approach[J]. IEEE Transactions on Engineering Management, 2019, 67(4): 1244−1255
31
Rottenstreich O. Sketches for blockchains[C]//Proc of the 2021 Int Conf on Communication Systems &amp; Networks. Piscataway, NJ: IEEE, 2021: 254−262
32
Lin Yibing, Huang C C, Tsai S C. SDN soft computing application for detecting heavy hitters[J]. IEEE Transactions on Industrial Informatics, 2019, 15(10): 5690−5699
33
Reviriego P, Martínez J, Rottenstreich O, et al. Remove minimum (RM): An error-tolerant scheme for cardinality estimate by HyperLogLog[J]. IEEE Transactions on Dependable and Secure Computing, 2020, 19(2): 966−977
34
Etherscan. The Ethereum blockchain explorer[EB/OL]. (2024-06-02)[2024-07-13]. https://etherscan.io
2024年第61卷第10期
74
38
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202440477
  • 接收时间:2024-06-05
  • 首发时间:2026-11-17
  • 出版时间:2024-10-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-05
  • 修回日期:2024-07-14
基金
作者信息
    1福州大学计算机与大数据学院 福州 350108
    2浙江大学计算机科学与技术学院 杭州 310013
    3浙江广播电视集团 杭州 310005
    4浙江大学工程师学院 杭州 310015
    5泉城实验室 济南 250103

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440477
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏