spe-222600 评估图像哈希和矢量数据库在改进石油和石油行业财务报表欺诈检测方面的有效性.pdfVIP

SPE-222600-MS

AssessingtheEffectivenessofImageHashingandVectorDatabases

inImprovingtheDetectionofFinancialStatementFraudintheOiland

PetroleumSector

DaliaAlbuqaytahandSarafudheenTharayil,CorporateApplicationsDepartment,SaudiAramco,Dhahran,Saudi

Arabia;MuhammadAzmiIdris,InformationsecurityDepartment,SaudiAramco,Dhahran,SaudiArabia

Copyright2024,SocietyofPetroleumEngineersDOI10.2118/222600-MS

ThispaperwaspreparedforpresentationattheADIPECheldinAbuDhabi,UAE,4–7November,2024.

ThispaperwasselectedforpresentationbyanSPEprogramcommitteefollowingreviewofinformationcontainedinanabstractsubmittedbytheauthor(s).Contents

ofthepaperhavenotbeenreviewedbytheSocietyofPetroleumEngineersandaresubjecttocorrectionbytheauthor(s).Thematerialdoesnotnecessarilyreflect

anypositionoftheSocietyofPetroleumEngineers,itsofficers,ormembers.Electronicreproduction,distribution,orstorageofanypartofthispaperwithoutthewritten

consentoftheSocietyofPetroleumEngineersisprohibited.Permissiontoreproduceinprintisrestrictedtoanabstractofnotmorethan300words;illustrationsmay

notbecopied.TheabstractmustcontainconspicuousacknowledgmentofSPEcopyright.

Abstract

Financialstatementfraudintheoilandpetroleumsectorposesasignificantchallenge,necessitating

advanceddetectionmethods.ThisstudyevaluatestheeffectivenessofintegratingtechniquesfromApproach

1andmethodsfromApproach2toenhancefrauddetectioninscannedfinancialdocuments.The

researchaddresseslimitationsofexistingrule-basedalgorithmsbyadoptinganovelhybridapproach.

Themethodologyincorporatesanencryptiontechniquetogenerateuniquecryptographyfordocument

images,enablingfraudevidenceidentificationthroughcryptographycomparisons.Thisiscomplementedby

generativeAI