Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200095825> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4200095825 endingPage "103612" @default.
- W4200095825 startingPage "103612" @default.
- W4200095825 abstract "Most existing deep neural networks are susceptible to the influence of adversarial examples, which may cause them to output incorrect prediction results. An adversarial example is the addition of small noise disturbances to the input data samples, which will deceive the classification. Generally, these modifications are very small noise disturbances, which are not easily noticed by the human eye. However, most existing adversarial attacks achieve only low success rates in typical black-box settings, where the attackers have no prior knowledge about the model structures and/or model parameters. To tackle this problem, we propose an iterative algorithm based on an acceleration gradient to enhance the adversary attack. Our method accumulates the gradient of the loss function in each iteration and uses the next gradient information to influence the future gradient. We also introduce the scaling invariance principle of a deep neural network to optimize the input images for black-box attacks. In addition, to handle the drawbacks of a traditional iterative fast gradient sign method, we further present two gradient optimization methods. Experimental results on the ImageNet dataset show that our attack methods can achieve good transferability. In addition, those models obtained by integrated adversarial training with strong defense capability are also quite vulnerable to our black-box attack." @default.
- W4200095825 created "2021-12-31" @default.
- W4200095825 creator A5017533320 @default.
- W4200095825 creator A5019024548 @default.
- W4200095825 creator A5029636776 @default.
- W4200095825 creator A5060263542 @default.
- W4200095825 creator A5061088108 @default.
- W4200095825 creator A5066083459 @default.
- W4200095825 creator A5066161906 @default.
- W4200095825 creator A5075512625 @default.
- W4200095825 creator A5076981458 @default.
- W4200095825 creator A5080571604 @default.
- W4200095825 date "2022-08-01" @default.
- W4200095825 modified "2023-10-17" @default.
- W4200095825 title "An efficient adversarial example generation algorithm based on an accelerated gradient iterative fast gradient" @default.
- W4200095825 cites W1998512010 @default.
- W4200095825 cites W2007303551 @default.
- W4200095825 cites W2040356629 @default.
- W4200095825 cites W2053459259 @default.
- W4200095825 cites W2257979135 @default.
- W4200095825 cites W2618530766 @default.
- W4200095825 cites W2766447205 @default.
- W4200095825 cites W2993903663 @default.
- W4200095825 cites W2998591333 @default.
- W4200095825 cites W3013199714 @default.
- W4200095825 cites W3013256492 @default.
- W4200095825 cites W3027378069 @default.
- W4200095825 cites W3043498557 @default.
- W4200095825 cites W3044541995 @default.
- W4200095825 cites W3095228482 @default.
- W4200095825 cites W3132102963 @default.
- W4200095825 cites W639708223 @default.
- W4200095825 doi "https://doi.org/10.1016/j.csi.2021.103612" @default.
- W4200095825 hasPublicationYear "2022" @default.
- W4200095825 type Work @default.
- W4200095825 citedByCount "17" @default.
- W4200095825 countsByYear W42000958252022 @default.
- W4200095825 countsByYear W42000958252023 @default.
- W4200095825 crossrefType "journal-article" @default.
- W4200095825 hasAuthorship W4200095825A5017533320 @default.
- W4200095825 hasAuthorship W4200095825A5019024548 @default.
- W4200095825 hasAuthorship W4200095825A5029636776 @default.
- W4200095825 hasAuthorship W4200095825A5060263542 @default.
- W4200095825 hasAuthorship W4200095825A5061088108 @default.
- W4200095825 hasAuthorship W4200095825A5066083459 @default.
- W4200095825 hasAuthorship W4200095825A5066161906 @default.
- W4200095825 hasAuthorship W4200095825A5075512625 @default.
- W4200095825 hasAuthorship W4200095825A5076981458 @default.
- W4200095825 hasAuthorship W4200095825A5080571604 @default.
- W4200095825 hasConcept C108583219 @default.
- W4200095825 hasConcept C11413529 @default.
- W4200095825 hasConcept C115961682 @default.
- W4200095825 hasConcept C126255220 @default.
- W4200095825 hasConcept C153258448 @default.
- W4200095825 hasConcept C154945302 @default.
- W4200095825 hasConcept C159694833 @default.
- W4200095825 hasConcept C33923547 @default.
- W4200095825 hasConcept C37736160 @default.
- W4200095825 hasConcept C41008148 @default.
- W4200095825 hasConcept C50644808 @default.
- W4200095825 hasConcept C94966114 @default.
- W4200095825 hasConcept C99498987 @default.
- W4200095825 hasConceptScore W4200095825C108583219 @default.
- W4200095825 hasConceptScore W4200095825C11413529 @default.
- W4200095825 hasConceptScore W4200095825C115961682 @default.
- W4200095825 hasConceptScore W4200095825C126255220 @default.
- W4200095825 hasConceptScore W4200095825C153258448 @default.
- W4200095825 hasConceptScore W4200095825C154945302 @default.
- W4200095825 hasConceptScore W4200095825C159694833 @default.
- W4200095825 hasConceptScore W4200095825C33923547 @default.
- W4200095825 hasConceptScore W4200095825C37736160 @default.
- W4200095825 hasConceptScore W4200095825C41008148 @default.
- W4200095825 hasConceptScore W4200095825C50644808 @default.
- W4200095825 hasConceptScore W4200095825C94966114 @default.
- W4200095825 hasConceptScore W4200095825C99498987 @default.
- W4200095825 hasLocation W42000958251 @default.
- W4200095825 hasOpenAccess W4200095825 @default.
- W4200095825 hasPrimaryLocation W42000958251 @default.
- W4200095825 hasRelatedWork W1561927205 @default.
- W4200095825 hasRelatedWork W2482350142 @default.
- W4200095825 hasRelatedWork W2502115930 @default.
- W4200095825 hasRelatedWork W3009622996 @default.
- W4200095825 hasRelatedWork W3126451824 @default.
- W4200095825 hasRelatedWork W3176240006 @default.
- W4200095825 hasRelatedWork W3184396788 @default.
- W4200095825 hasRelatedWork W4246396837 @default.
- W4200095825 hasRelatedWork W4377865163 @default.
- W4200095825 hasRelatedWork W4379538695 @default.
- W4200095825 hasVolume "82" @default.
- W4200095825 isParatext "false" @default.
- W4200095825 isRetracted "false" @default.
- W4200095825 workType "article" @default.