Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics

Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics

ID:40707213

大小:4.90 MB

页数:9页

时间:2019-08-06

Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics _第1页
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics _第2页
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics _第3页
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics _第4页
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics _第5页
资源描述:

《Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics 》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、AdversarialExamplesDetectioninDeepNetworkswithConvolutionalFilterStatisticsXinLi,FuxinLiSchoolofElectricalEngineeringandComputerScienceOregonStateUniversityurumican@gmail.com,lif@eecs.oregonstate.eduAbstractDeeplearninghasgreatlyimprovedvisualrecognitioninrecen

2、tyears.However,recentresearchhasshownthatthereexistmanyadversarialexamplesthatcannegativelyimpacttheperformanceofsuchanarchitecture.Thispaperfocusesondetectingthoseadversarialexamplesbyanalyz-ingwhethertheycomefromthesamedistributionasthenormalexamples.Insteado

3、fdirectlytrainingadeepneuralFigure1.Anoptimizationalgorithmcanfindtheadversarialex-networktodetectadversarials,amuchsimplerapproachisamplewhere,withalmostnegligibleperturbationstohumaneyes,proposedbasedonstatisticsonoutputsfromconvolutionalwillcompletelydistortt

4、hepredictionresultofadeepneuralnet-layers.Acascadeclassifierisdesignedtoefficientlydetectwork[26].Thisalgorithmisquiteuniversal,havingbeensuccess-adversarials.Furthermore,trainedfromoneparticularad-fullytestedonmanydifferentnetworksandtheusercandirecttheversarial

5、generatingmechanism,theresultingclassifiercannetworktooutputanycategorywithadversarialoptimization.successfullydetectadversarialsfromacompletelydifferentmechanismaswell.Afterdetectingadversarialexamples,andotherdevastatingeffectswouldbeunavoidable.weshowthatmany

6、ofthemcanberecoveredbysimplyper-formingasmallaveragefilterontheimage.Thosefind-Therefore,thereareamplereasonstobelievethatitisingsshouldprovokeustothinkmoreabouttheclassificationimportanttoidentifywhetheranexamplecomesfromanor-mechanismsindeepconvolutionalneuralne

7、tworks.maloranadversarialdistribution.Suchknowledgeifavail-ablewillhelpsignificantlytocontrolbehaviorsofrobotsemployingdeeplearning.Areliableprocedurecanpreventrobotsfrombehavinginundesirablemannersundesirable1.Introductionbecauseofthefalseperceptionsitmadeabout

8、theenviron-Recentadvancesindeeplearninghavegreatlyimprovedment.arXiv:1612.07767v1[cs.CV]22Dec2016thecapabilitytorecognizeimagesautomatically[13,24,8].Theunderstandingofwheth

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。