Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967398859> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2967398859 abstract "In recent years, Deep Learning has presented impressive performance when solving complex image classification and recognition tasks in decision support systems. Nonetheless, studies have demonstrated Deep Learning models are susceptible to attacks conducted with adversarial images, i.e. images containing subtle perturbations in order to induce models to misclassification. The main existing countermeasures against adversarial images have shown ineficiency, permitting attackers to map their internal operation more easily. Therefore, this work aims to evaluate a defense method called MultiMagNet which randomly incorporates at runtime multiple defense components, implemented as autoencoders, in order to introduce an expanded form of non-determinism behavior for hindering evasions of adversarial nature. Experiments on CIFAR-10 dataset showed MultiMagNet was able to detect images generated by different attack algorithms." @default.
- W2967398859 created "2019-08-22" @default.
- W2967398859 creator A5006106551 @default.
- W2967398859 creator A5077120128 @default.
- W2967398859 creator A5083359779 @default.
- W2967398859 date "2019-05-20" @default.
- W2967398859 modified "2023-09-26" @default.
- W2967398859 title "A Non-Deterministic Method to Construct Ensemble-Based Classifiers to Protect Decision Support Systems Against Adversarial Images" @default.
- W2967398859 cites W2070381776 @default.
- W2967398859 cites W2243397390 @default.
- W2967398859 cites W2562774313 @default.
- W2967398859 cites W2603766943 @default.
- W2967398859 cites W2607219512 @default.
- W2967398859 cites W2618043096 @default.
- W2967398859 cites W2768148056 @default.
- W2967398859 cites W2783471871 @default.
- W2967398859 cites W2794569859 @default.
- W2967398859 cites W2963564844 @default.
- W2967398859 cites W2963857521 @default.
- W2967398859 cites W2964082701 @default.
- W2967398859 doi "https://doi.org/10.1145/3330204.3330282" @default.
- W2967398859 hasPublicationYear "2019" @default.
- W2967398859 type Work @default.
- W2967398859 sameAs 2967398859 @default.
- W2967398859 citedByCount "1" @default.
- W2967398859 countsByYear W29673988592021 @default.
- W2967398859 crossrefType "proceedings-article" @default.
- W2967398859 hasAuthorship W2967398859A5006106551 @default.
- W2967398859 hasAuthorship W2967398859A5077120128 @default.
- W2967398859 hasAuthorship W2967398859A5083359779 @default.
- W2967398859 hasConcept C115961682 @default.
- W2967398859 hasConcept C119857082 @default.
- W2967398859 hasConcept C153180895 @default.
- W2967398859 hasConcept C154945302 @default.
- W2967398859 hasConcept C199360897 @default.
- W2967398859 hasConcept C2778403875 @default.
- W2967398859 hasConcept C2780801425 @default.
- W2967398859 hasConcept C37736160 @default.
- W2967398859 hasConcept C41008148 @default.
- W2967398859 hasConcept C75294576 @default.
- W2967398859 hasConceptScore W2967398859C115961682 @default.
- W2967398859 hasConceptScore W2967398859C119857082 @default.
- W2967398859 hasConceptScore W2967398859C153180895 @default.
- W2967398859 hasConceptScore W2967398859C154945302 @default.
- W2967398859 hasConceptScore W2967398859C199360897 @default.
- W2967398859 hasConceptScore W2967398859C2778403875 @default.
- W2967398859 hasConceptScore W2967398859C2780801425 @default.
- W2967398859 hasConceptScore W2967398859C37736160 @default.
- W2967398859 hasConceptScore W2967398859C41008148 @default.
- W2967398859 hasConceptScore W2967398859C75294576 @default.
- W2967398859 hasLocation W29673988591 @default.
- W2967398859 hasOpenAccess W2967398859 @default.
- W2967398859 hasPrimaryLocation W29673988591 @default.
- W2967398859 hasRelatedWork W2799266338 @default.
- W2967398859 hasRelatedWork W2948798712 @default.
- W2967398859 hasRelatedWork W2953920146 @default.
- W2967398859 hasRelatedWork W2963960272 @default.
- W2967398859 hasRelatedWork W3013617128 @default.
- W2967398859 hasRelatedWork W3172173631 @default.
- W2967398859 hasRelatedWork W4224883155 @default.
- W2967398859 hasRelatedWork W4225586443 @default.
- W2967398859 hasRelatedWork W4300687258 @default.
- W2967398859 hasRelatedWork W4379255972 @default.
- W2967398859 isParatext "false" @default.
- W2967398859 isRetracted "false" @default.
- W2967398859 magId "2967398859" @default.
- W2967398859 workType "article" @default.