TowardsDefendingagainstAdversarialExamplesviaAttack-InvariantFeatures455DaweiZhou12Ton8g9li1angLiu2BoHan3Nanna5nWang1†5ChunleiPeng4XinboGao55AbstractTruckAutomobilePGD??ShipAADeepneuralnetworks(...
RobustPolicyGradientagainstStrongDataCorruptionXuezhouZhang1YidingChen1JerryZhu1WenSun2Abstracthighlynoisydata,suchasautonomousdriving,quantitativetrading,ormedicaldiagnosis.Westudytheproblemofrobu...
OnlineSelectionProblemsagainstConstrainedAdversaryZhihaoJiang1PinyanLu2ZhihaoGavinTang2YuhaoZhang3Abstractlearnedadvicetoonlinealgorithmdesigns.Inparticular,thealgorithmisgivensomeextrainformationa...
LearningtoPriceagainstaMovingTargetRenatoPaesLeme1BalasubramanianSivan1YifengTeng2PratikWorah1Abstractparametricnoise(Shahetal.,2019;Krishnamurthyetal.,2020).Allthosemodelsarestationaryinthesenseth...
KnowledgeEnhancedMachineLearningPipelineagainstDiverseAdversarialAttacksNeziheMerveGu¨rel1XiangyuQi2LukaRimanic1CeZhang1BoLi3Abstract1.IntroductionDespitethegreatsuccessesachievedbydeepneu-Recents...
EfficientTrainingofRobustDecisionTreesagainstAdversarialExamplesDanie¨lVos1SiccoVerwer1Abstractetal.,2019),wecloselymimicthegreedyrecursivesplit-tingstrategythattraditionaldecisiontreesuseandwesco...
SPECTRE:DefendingagainstBackdoorAttacksUsingRobustStatisticsJonathanHayase1WeihaoKong1RaghavSomani1SewoongOh1AbstractaccuracyonpoisonedtestexamplesStartingwiththeseminalworkof(Guetal.,2017),thereha...
CRFL:CertifiablyRobustFederatedLearningagainstBackdoorAttacksChulinXie1MinghaoChen2Pin-YuChen3BoLi1AbstractCRFLTrainingCRFLTestingFederatedLearning(FL)asadistributedlearn-ModelUpdatesParameteringpa...
Second-OrderProvableDefensesagainstAdversarialAttacksSahilSingla1SoheilFeizi1Abstract1.IntroductionArobustnesscertificateagainstadversarialexam-Modernneuralnetworksachievehighaccuracyontasksplesist...
RandomizationmattersHowtodefendagainststrongadversarialattacksRafaelPinot12RaphaelEttedgui1GeovaniRizk1YannChevaleyre1JamalAtif1Abstractand(Szegedyetal.,2014)itbecameincreasinglyimportanttoundersta...
Bisection-BasedPricingforRepeatedContextualAuctionsagainstStrategicBuyerAntonZhiyanov12AlexeyDrutsa12AbstractMunoz,2014;Drutsa,2018)),asecond-priceauctionwithreservepricesreducestoaposted-priceauct...
AdversarialRobustnessagainsttheUnionofMultiplePerturbationModelsPratyushMaini1EricWong2J.ZicoKolter34Abstracttheexistenceofdatapointswhichcanbeadversariallyper-turbedtobemisclassified,butare“close...
AdaptiveReward-PoisoningAttacksagainstReinforcementLearningXuezhouZhang1YuzheMa1AdishSingla2XiaojinZhu1AbstractgroupofTwitteruserswhodeliberatelytaughtitmisogynis-ticandracistremarksshortlyafterits...
RobustDecisionTreesagainstAdversarialExamplesHonggeChen1HuanZhang2DuaneBoning1Cho-JuiHsieh2Abstracttherobustnessoftree-basedmodelsarequitelimited(Paper-notetal.,2016a).Althoughadversarialexamplesan...
OnCertifyingNon-uniformBoundsagainstAdversarialAttacksChenLiu1RyotaTomioka2VolkanCevher1AbstractCWattack(Carlini&Wagner,2017).MostattackmethodssearchfortheadversarialexamplebyutilizingthegradientTh...
HowdoesDisagreementHelpGeneralizationagainstLabelCorruption?XingruiYu1BoHan2JiangchaoYao3GangNiu2IvorW.Tsang1MasashiSugiyama24Abstractthesecomplexmodelscanfullymemorizenoisylabels(Zhangetal.,2017;A...
DefendingagainstSaddlePointAttackinByzantine-RobustDistributedLearningDongYin1YudongChen2KannanRamchandran1PeterBartlett13Abstractarestoredandprocessedlocallyinendusers’cellphonesandpersonalcomput...
CompetingagainstEquilibriainZero-SumGameswithEvolvingPayoffsAdrianRiveraCardoso1JacobAbernethy2HeWang1HuanXu1Abstractsumgames,wheretheunderlyingpayoffmatrixisoftenassumedtobefixedori.i.d.Incontrast...
ProvableDefensesagainstAdversarialExamplesviatheConvexOuterAdversarialPolytopeEricWong1J.ZicoKolter2Abstract1.IntroductionWeproposeamethodtolearndeepReLU-basedRecentworkindeeplearninghasdemonstrate...