




版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领
文档简介
GenerativeAIandCybersecurity:
Arevisitedclassic
ThegreatestriskswhenincorporatinggenerativeAIintoabusinessstructureare:
Misleadingoutcomesduetomodelhallucination
Dataleakageandcopyrightissuesduetounintentionaldisseminationorinclusionofregulatedor
company-confidentialdata
Trainingdata–subjects’privacyandconsentviolationswith
Modelcorruptionandabusewhenretrainingisbasedoncustomerresponsedata
AI
inadequateneed-to-knowandneed-to-useintrainingdataanddataoutputsmanagement
MeetingregulatoryandethicalresponsibilitiesinGenAIuse
Ethicalissuesorbiased
conclusionsbecauseofinaccurate,
incomplete,ortamperedtrainingdata
Thebiggest
risksaretodata
WhendesigningforsecuregenerativeAI,datariskstakepriority.Broadlyspeaking,theserisksoriginatefromthreeactivities:
Theexposureofconfidentialand/orregulatedinformation
Inaccurateinformationdisruptsprocesses,whetherdecisionaloroperational
GenAIfollowsafamiliarpatternforadoptionandcybersecurity,
promptingquestionsreminiscentofthosethataccompaniedthe
earlydaysofcloudcomputing.TherapidriseofgenerativeAI
presentsorganizationswiththeusualinnovationdilemma:isit
bettertoadoptacautiousandrestrictiveapproach,riskingmissingoutonopportunities,ortograntmorefreedom,attheriskof
exposingthemselvestonewrisks?
PotentialreputationaldamageiscausedwhenGenAItoolsareusedaschatbotsservingasinterfacesbetweencustomersandanorganization
Theseriskshavecommonthemesofidentifying,scrubbing,andprotectingtherightdataatthe
righttimeandputtingtherightguardrailsinplacearoundaGenAIsolution.Despiteitspotentialandtheexcitementsurroundingit,GenAIisultimatelyanotherenterprisetool:itrequirestheapplicationandadaptationofpolicies,controlsandmeasures
implementedatenterpriselevelandwithintheAIecosystem.Itbringschallengesofoperatingmodelsinternallyandmonitoringtheirinputandoutputcompliantly.
InaGenAIsystem,foundationalsecuritymustbedoneacrossfourdimensions:
.Framework,governance,andriskmanagement
.Dataandidentitysecurity
.TrustedGenAImodelsandtheiroutcomes
.Infrastructureandapplicationmonitoringanddelivery
ThreatmodelsareavailablefromNIST,MITRE,
Microsoft,Google,andothersintheindustrytobuildfasterandbereadyfornewrisks.
AGenAIsystemcanhavedifferentsecurityscopes.Usingcloudserviceproviders(CSP)asexamples,eachCSP(alsoknownashyperscalers)offersgenerative
AIsystemswithverydifferentsecurityscopes,
andeachproviderdefinesthisscopedifferently.
ConsidersharedresponsibilityaroundthereferencearchitecturefoundinFigure1.
2|GenerativeAI&Cybersecurity
GenerativeAI&Cybersecurity|3
Data
Datacollection,datapreparationandtransformation
Varioususecasesthatmatterstotheendusersandarerelevantbusinesscases
modelsthataretailoredtoagivenindustryorusecaseToolstooperationalizeGen-AImodels
Gen-AIapplicationssuchascompute,networkandstorage
Applications
SoftwareapplicationsthatprimarilyuseGen-AImodelstoperformatask
Monitoring&Maintain
Monitorperformance,userexperienceandoutcomequality
Models&Tools
Gen-AIfoundationmodels&domainspecific
Infrastructure
Infrastructurecomponentsusedtobuildout
Network
Communication
Storage
Compute
Figure1:ConceptualreferencearchitectureforGenAIsharedresponsibility.
AmazonWebServicesfocusesonprovidingthe
infrastructureforgenerativeAImodels,aswith
AmazonBedrock.Variousdegreesofcustomizationandownershiparepossible.Theclient’ssystemis
definedastheprovidedinfrastructure,andtheirpartofsharedresponsibilityincludesthesecurityofthemodels,data,andapplications.
GoogleCloudPlatform’s(GCP)approachfocusesontheinfrastructureandmodels,offeringVertexAIandtheModelGardentoempowercustomers.Customers
focusontheapplicationlayer,monitoring,andtheGenAIinterface,whileGCPhassharedresponsibilityfromthemodeldowntodataandinfrastructure.
WithMicrosoftAzure’sCo-pilot,theCSPtakes
ownershipofinfrastructure,model,application,and
everythinginbetween..Thecustomerfocusesondatasecurityandbusinesspurposes.Datainterfacesdefinetheirsystem,whilethemodels,infrastructure,and
applicationinterfacearetreatedmoreasblackboxes.
4|GenerativeAI&CybersecurityGenerativeAI&Cybersecurity|5
Establishing
asecurity
frameworkwithgovernance
PositionsonhowtoregulateGenAIvarywidely,
fromoutrightprohibitiontocompletelaissez-faire.Nosinglegovernmentorsupranationalpolitical
entitywillbeabletodictatehowGenAIproliferates.Nevertheless,enterprisesmustworkwithinlegal
andregulatorystructuresbasedontheirclients,geographies,andethics.
Toanticipatewhat’sexpectedingenerativeAIgovernance,enterprisesshouldconsiderthefollowing:
.ExistingandupcomingregulationsthatwillinfluenceAIuse
.Anenterprise’suniquerisktolerancesfortechnologyandregulations
.TeammembereducationonhowGenAIworks,itsinherentproblems,andriskssuchasdataleaksandtheorganization’sownpolicies
.AsecureGenAIreferencearchitecturedescribinghowtomanagerisks
Thereferencearchitecturemustaddresstherisksofvariousmodelsindiverseways.Afullproprietarysolution,includingGenAImodeldevelopmentandpre-training,meansanorganizationwillhavethe
abilityandobligationtoaddressitsspecificrisksend-to-end.
InthecaseofSoftware-as-a-ServicegenerativeAI,manyrisksneedtobeaddressedthroughcontractandthird-andfourth-partyriskmanagement.
OrganizationscanalsodeploymorethanoneGenAIsolutionwithdifferentarchitecturemodels,andhybridmodels.
Governancebodies-suchasaGenerativeAICenterofExcellence-areneededinenterprisestohelpshape
thesecureadoptionofGenAI.Theyhelpaccelerate
low-risk,high-impactbusinessexperimentswhile
enforcingappropriateoversightofhigh-riskplans.Bydevelopingrepeatable,enforceable,anddisseminatedguidelines,enterprisescanleverageGenAIsolutionsmorequicklyandsecurely.
Providerassumedresponsibility
SaaS
ExternalModel
PaaS
IaaS
Applications
Monitoring&Maintain
Models&Tools
Data
Infrastructure
M
Network
Communication
Storage
Compute
Figure2:SharedresponsibilitymodelsforvariouscloudproviderGenAIdeliverymodels
6|GenerativeAI&CybersecurityGenerativeAI&Cybersecurity|7
SecuringData
GenAIlackshumanfilterswhenitproducesdata:themachinesearchesthrougheverythingitcanaccess
andthenreproducesthisknowledgewithcompletecandorregardlessofsensitivity.Itis,therefore,
imperativetosetlimits.Todothis,enterprisesmust
inventorytheirdata:classifyit;implementcontrolsforquality,representativeness,integrity,andaccess;andcreaterepositoriesofauthorizeddataforGenAIapplications.
GenAI’sconsumptionofdatamakesdata
classificationevenmoreessentialtoadequately
protectanenterpriseandcustomers.Classification
allowstightercontrolofdatausedtotrain,specialize,andrefinemodels.Accesstoitsoutputcanbe
restrictedanddataleakprotectiontoolscanbe
implemented;oraresponsecanbelimitedusingasubsetofdatabasedonaright-to-knowrule.
Withathird-partyLLM,thereislimitedabilityto
build“native”guardrailsaroundinputsandoutputs.Likewise,theabilitytoimplementguardrailsinsidethelearningphasesofaGenerativeAdversarial
Network1islimitedwhenusingclosedmodelsinan
Data
1.Training
Themodelisbuiltwhich
encodestherealtionships,
patternsandsequences
withintrainingdataand
modelvalidationdata.
●
TrainedModel
●
3.EnsuringCorrectness
Thereisnoguranteeofreal-worldcorrectnessfromagenerativeAImodels,anditsometimes
hallucinatesfictionalresponse
2.Generation
Thetrainedmodelcanthengeneratenewoutputsliketheoriginaldataitwastrainedon
(Optional)
FineTuning
Thegenericfoundation
modelmightbefine-tuned
togiveitexposuretoa
specialistarea.
(Optional)Alignment
Modelmightbetweaked
toaligninmorewith
expectedhumanresponse
Figure3:DatalifecycleinsideagenerativeAIapplication
application.Itiscriticaltoconsiderwhetherdata
canbeinspectedandvalidated,andwhetherits
inputsandoutputscanbeobservedwhenchoosingcomponentsofasystem.
Amodel’soutputmustbesubjecttoverification
todetecthallucinations,maliciousreinforcement,
ordriftsfromexpectedbehaviorovertime.When
usingreal-timemodeloutput,suchaswithachatbot,theobservabilityofpastperformancetopreempt
unacceptableresponsesisimportant.Akeypointis
tounderstandthedatalifecycleanditssensitivity,ascapturedinFigure3.Datasecurityrequirementscanchangeoveritslifecycle,dependingonitsproximityto,orcominglingwithotherdata.
SuccessfullysecuringGenAIsolutionsisamulti-
disciplineapproachthatrequirespartnerships
betweencybersecurity,datagovernance,data
science,andlegalandcompliance,sincedisciplineddatamanagementisattheheartofachievingGenAIdatasecurity.
Dependencies
Data
Governance
Data
Sciences
Security
Legal&Compliance
Figure4:Multi-disciplineinteractionsnecessaryforGenAIsuccess
8|GenerativeAI&CybersecurityGenerativeAI&Cybersecurity|9
TrustedGen
AImodelsandtheiroutcomes
Itmaynotbepossibletogainaccesstoandthen
validatealldatasetsusedduringthelifecycleof
aGenAIsolution.Amodelsuchasthecommonly
usedLargeLanguageModel(LLM),multi-model
models,andtransformer-basedmodelsgeneratingoutcomesthroughuserpromptorAPIrequestscanfallintooneofthefollowingmodelcategories:
.Developedandinitiallytrainedbyanexternal
party(OpenAI’sChatGPT,forinstance)andused“asis”bytheenterprise
.Developedandinitiallytrainedbyanexternal
party,thenspecializedbytheenterprisetoa
specificdomain(i.e.,specialism)withanewdatasettoaddressspecificusecases
.DevelopedandtrainedbytheenterpriseentirelySupplychainsecurityandthird/fourth-partyrisk
managementarecrucialforthefirsttwocategories.
Itisevenmoreimportanttointegratesecuritycontrolssuchasmodelauditability,dataleakageprevention,hallucinationandbiasdetection(i.e.guardrails)intotheapplicationdevelopment
pipeline.
Dataquality
Therecurrentuseandprovenanceoftrainingdataisafocalpointwhenusingexternallysourcedmodels.Itscomposition,howoftenitchanges,andhowrecursionbetweencustomerprompt/responsepairingsand
reinforcementtrainingofthemodeloccursshouldbeclear.
Whendevelopingandtrainingaproprietarymodel(thirdcategoryabove),someriskscanbeamplifiedwhileothersaremitigated.Theneedtounderstanddata’sprovenanceandclassificationoftrainingdatawhilealsotestingforbiasandderogatoryresponsesfallsontheenterprise,eventhoughthosecanbe
differentdisciplines.Atthesametime,therisks
ofrecursivetrainingfromprompt/responsepairsarereducedastheinformationdoesn’tleavethelocalmodel.
Forallmodels,organizationsmustapplytheirownadditional,adaptablecontrols,suchas:
.Specificsecuritymonitoringrules
.Completelyoriginalmeasures,suchascontrolstodetectspecificnewattacksoruserbehaviors.
.Formultiandhybridarchitectures,APIsecurityandCI/CDsecure-by-designdomains
Thekeytoassuranceofdata’sintegrityisdue
diligenceonaprovider’ssecurity,privacycontrols,andcompliance.Theircommitmentsandresponsibilities
shouldbeclearlydefinedinanycontract.
10|GenerativeAI&CybersecurityGenerativeAI&Cybersecurity|11
Application
and
infrastructuremonitoring
anddelivery
ThefinalaspectofsecurityforGenAIisprotecting
applicationsfrombeingrenderedinoperativeor
unavailable.Thisrequiresdeployingsecuritycontrolswithinapplicationsandinfrastructure,covering
compute,endpoint,network,andstorage.
Thesamesecurityandcompliancehygieneappliedtoclassicsecuritymustbeappliedhere,especiallythosehandlingsensitivedata.Corporatesecurity
policiesandmandatorysecuritycontrolsovertheselayersareasimportantasever.
GenAIapplicationswillrequiresomenewsecuritycontrols,suchaspromptanalysis,andadaptationto
existingsecuritycontrols,suchasedgeprotection,tobeeffective.Buildingadequate,automated
governancearounddataclassificationandusageshouldbepartofanysecurityroadmap.
SoftwaresupplychainmanagementismoreimportantingenerativeAIapplicationdevelopment,e.g.,for
pinningdependencyversionsinmodeldevelopmenttoensuretrainingrunsdonotbecomecorrupted.Thisisimportantformonitoringanddeliverysinceitisa
partofthesoftwaredeliverylifecycle.Continuous
Integration(CI)andcontinuousdelivery(CD)throughaDevSecOpspipelineforapplicationdevelopment
canbeusedtosecuremodeldevelopment.Red
teaming2,anapplicationtotestforvulnerabilities,shouldincludetestingofanyprompts.Thisaimstostopmalicioususersfrom:
.Corruptingorrecoveringtrainingdata
.Manipulatingresultsforotherusers
.Performingdenialofserviceattacks
.Exfiltratingdata
AsgenerativeAIevolves,securityfunctionsnativetoGenAIwilltoo,aswilltheircapabilitiestointegratewithexternalsecuritysolutions.
12|GenerativeA
温馨提示
- 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
- 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
- 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
- 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
- 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
- 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
- 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
最新文档
- 中国红王子锦带花项目创业计划书
- 中国家用呼吸机项目创业计划书
- 中国空管项目创业计划书
- 中国计算机外设项目创业计划书
- 中国牛床垫项目创业计划书
- 2025精简版专利权合同
- 青海饲料项目创业计划书
- 互联网人工智能服务使用风险提示合同书
- 稀土资源的未来潜力研究-洞察阐释
- 农村小区土地流转合同协议
- DB51T 1466-2012 马尾松二元立木材积表、单木出材率表
- 初中常见副词英语单选题100道及答案解析
- 《有机化学》课件-第九章 醛和酮
- 文献管理与信息分析学习通超星期末考试答案章节答案2024年
- 创业管理实战学习通超星期末考试答案章节答案2024年
- 直播助农创业计划书
- 公路水泥混凝土路面施工技术规范(JTGF30-2024)
- 弱电监控系统工程施工组织计划书
- 代销销售合同协议书
- 广东省珠海市香洲区2023-2024学年七年级下学期期末历史试题(原卷版)
- 反诉状(业主反诉物业)(供参考)
评论
0/150
提交评论