Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285819292> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4285819292 endingPage "618" @default.
- W4285819292 startingPage "606" @default.
- W4285819292 abstract "As deep neural networks (DNNs) become more widely used in various safety-critical applications, protecting their security has been an urgent and important task. Recently, one critical security issue is proposed that DNN models are vulnerable to targeted bit-flip attacks. This kind of sophisticated attack tries to inject backdoors into models via flipping only a few bits of carefully chosen model parameters. In this paper, we propose a gradient obfuscation-based data augmentation method to mitigate these targeted bit-flip attacks as an empirical study. Particularly, we mitigate such targeted bit-flip attacks by preprocessing only input samples to break the link between the features carried by triggers of input samples with the modified model parameters. Moreover, our method can keep an acceptable accuracy on benign samples. We show that our method is effective against two targeted bit-flip attacks by experiments on two widely-used structures (ResNet-20 and VGG-16) with one famous dataset (CIFAR-10)." @default.
- W4285819292 created "2022-07-19" @default.
- W4285819292 creator A5019692903 @default.
- W4285819292 creator A5020279524 @default.
- W4285819292 creator A5063923009 @default.
- W4285819292 creator A5083330935 @default.
- W4285819292 creator A5091382315 @default.
- W4285819292 date "2022-01-01" @default.
- W4285819292 modified "2023-10-17" @default.
- W4285819292 title "Mitigating Targeted Bit-Flip Attacks via Data Augmentation: An Empirical Study" @default.
- W4285819292 cites W2008164459 @default.
- W4285819292 cites W2157116240 @default.
- W4285819292 cites W2194775991 @default.
- W4285819292 cites W2401520370 @default.
- W4285819292 cites W2537014044 @default.
- W4285819292 cites W2753783305 @default.
- W4285819292 cites W2939184879 @default.
- W4285819292 cites W2942091739 @default.
- W4285819292 cites W2963240573 @default.
- W4285819292 cites W2963857521 @default.
- W4285819292 cites W2981860227 @default.
- W4285819292 cites W3002072934 @default.
- W4285819292 cites W3034579202 @default.
- W4285819292 cites W3034665124 @default.
- W4285819292 cites W3041173183 @default.
- W4285819292 cites W3045889720 @default.
- W4285819292 cites W3115360974 @default.
- W4285819292 cites W3135550350 @default.
- W4285819292 cites W3163711566 @default.
- W4285819292 cites W3163966458 @default.
- W4285819292 cites W4214737857 @default.
- W4285819292 cites W4241644338 @default.
- W4285819292 cites W4252979261 @default.
- W4285819292 doi "https://doi.org/10.1007/978-3-031-10989-8_48" @default.
- W4285819292 hasPublicationYear "2022" @default.
- W4285819292 type Work @default.
- W4285819292 citedByCount "1" @default.
- W4285819292 crossrefType "book-chapter" @default.
- W4285819292 hasAuthorship W4285819292A5019692903 @default.
- W4285819292 hasAuthorship W4285819292A5020279524 @default.
- W4285819292 hasAuthorship W4285819292A5063923009 @default.
- W4285819292 hasAuthorship W4285819292A5083330935 @default.
- W4285819292 hasAuthorship W4285819292A5091382315 @default.
- W4285819292 hasConcept C117011727 @default.
- W4285819292 hasConcept C124101348 @default.
- W4285819292 hasConcept C127413603 @default.
- W4285819292 hasConcept C154945302 @default.
- W4285819292 hasConcept C201995342 @default.
- W4285819292 hasConcept C2780451532 @default.
- W4285819292 hasConcept C34736171 @default.
- W4285819292 hasConcept C38652104 @default.
- W4285819292 hasConcept C40305131 @default.
- W4285819292 hasConcept C41008148 @default.
- W4285819292 hasConceptScore W4285819292C117011727 @default.
- W4285819292 hasConceptScore W4285819292C124101348 @default.
- W4285819292 hasConceptScore W4285819292C127413603 @default.
- W4285819292 hasConceptScore W4285819292C154945302 @default.
- W4285819292 hasConceptScore W4285819292C201995342 @default.
- W4285819292 hasConceptScore W4285819292C2780451532 @default.
- W4285819292 hasConceptScore W4285819292C34736171 @default.
- W4285819292 hasConceptScore W4285819292C38652104 @default.
- W4285819292 hasConceptScore W4285819292C40305131 @default.
- W4285819292 hasConceptScore W4285819292C41008148 @default.
- W4285819292 hasLocation W42858192921 @default.
- W4285819292 hasOpenAccess W4285819292 @default.
- W4285819292 hasPrimaryLocation W42858192921 @default.
- W4285819292 hasRelatedWork W2060012464 @default.
- W4285819292 hasRelatedWork W2072721176 @default.
- W4285819292 hasRelatedWork W2081647779 @default.
- W4285819292 hasRelatedWork W2382007173 @default.
- W4285819292 hasRelatedWork W2382928216 @default.
- W4285819292 hasRelatedWork W2384383430 @default.
- W4285819292 hasRelatedWork W2783233264 @default.
- W4285819292 hasRelatedWork W2914291315 @default.
- W4285819292 hasRelatedWork W4237750775 @default.
- W4285819292 hasRelatedWork W4313128243 @default.
- W4285819292 isParatext "false" @default.
- W4285819292 isRetracted "false" @default.
- W4285819292 workType "book-chapter" @default.