ObfuscatedGradientsGiveaFalseSenseofSecurity:CircumventingDefensestoAdversarialExamplesAnishAthalye1NicholasCarlini2DavidWagner2Abstractapparentrobustnessagainstiterativeoptimizationattacks:obfusca...
DoesDistributionallyRobustSupervisedLearningGiveRobustClassifiers?WeihuaHu12GangNiu2IsseiSato12MasashiSugiyama21AbstractDistributionallyRobustSupervisedLearning(DRSL)isapromisingparadigmtotacklethi...