FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209367351> ?p ?o ?g. }

• W3209367351 endingPage "4276" @default.
• W3209367351 startingPage "4253" @default.
• W3209367351 abstract "The widespread application of deep neural network (DNN) techniques is being challenged by adversarial examples—the legitimate input added with imperceptible and well-designed perturbation that can fool DNNs easily in the DNN testing/deploying stage. Previous white-box adversarial example generation algorithms used the Jacobian gradient information to add the perturbation. This imprecise and inexplicit information can cause unnecessary perturbation when generating adversarial examples. This paper aims to address this issue. We first propose to apply the more informative and distilled gradient information, namely, integrated gradient, to generate adversarial examples. To further make the perturbation more imperceptible, we propose to employ the restriction combination of L 0 and L 1 / L 2 second, which can restrict the total perturbation and the perturbation points simultaneously. Meanwhile, to address the nondifferentiable problem of L 1 , we explore a proximal operation of L 1 third. On the basis of these three works, we propose two Integrated gradient-based White-box Adversarial example generation algorithms (IWA): Integrated gradient-based Finite Point Attack (IFPA) and Integrated gradient-based Universe Attack (IUA). IFPA is suitable for situations where there are a determined number of points to be perturbed. IUA is suitable for situations where no perturbation point number is preset to obtain more adversarial examples. We verify the effectiveness of the proposed algorithms on both structured and unstructured data sets, and compare them with five baseline generation algorithms. The results show that our proposed algorithms craft adversarial examples with more imperceptible perturbation and satisfactory crafting rate. L 2 restriction is suitable for unstructured data sets and L 1 restriction performs better in the structured data set." @default.
• W3209367351 created "2021-11-08" @default.
• W3209367351 creator A5017004453 @default.
• W3209367351 creator A5024597522 @default.
• W3209367351 creator A5052107829 @default.
• W3209367351 creator A5085845806 @default.
• W3209367351 date "2021-10-28" @default.
• W3209367351 modified "2023-09-27" @default.
• W3209367351 title "IWA: Integrated gradient‐based white‐box attacks for fooling deep neural networks" @default.
• W3209367351 cites W2055637560 @default.
• W3209367351 cites W2099940443 @default.
• W3209367351 cites W2112796928 @default.
• W3209367351 cites W2114515438 @default.
• W3209367351 cites W2180612164 @default.
• W3209367351 cites W2194775991 @default.
• W3209367351 cites W2243397390 @default.
• W3209367351 cites W2744095836 @default.
• W3209367351 cites W2746600820 @default.
• W3209367351 cites W2763081248 @default.
• W3209367351 cites W2792942633 @default.
• W3209367351 cites W2800912855 @default.
• W3209367351 cites W2945645805 @default.
• W3209367351 cites W2963178695 @default.
• W3209367351 cites W2963857521 @default.
• W3209367351 cites W2964082701 @default.
• W3209367351 cites W2964301649 @default.
• W3209367351 cites W3034571331 @default.
• W3209367351 cites W3103557498 @default.
• W3209367351 doi "https://doi.org/10.1002/int.22720" @default.
• W3209367351 hasPublicationYear "2021" @default.
• W3209367351 type Work @default.
• W3209367351 sameAs 3209367351 @default.
• W3209367351 citedByCount "5" @default.
• W3209367351 countsByYear W32093673512021 @default.
• W3209367351 countsByYear W32093673512022 @default.
• W3209367351 crossrefType "journal-article" @default.
• W3209367351 hasAuthorship W3209367351A5017004453 @default.
• W3209367351 hasAuthorship W3209367351A5024597522 @default.
• W3209367351 hasAuthorship W3209367351A5052107829 @default.
• W3209367351 hasAuthorship W3209367351A5085845806 @default.
• W3209367351 hasBestOaLocation W32093673511 @default.
• W3209367351 hasConcept C11413529 @default.
• W3209367351 hasConcept C121332964 @default.
• W3209367351 hasConcept C154945302 @default.
• W3209367351 hasConcept C177918212 @default.
• W3209367351 hasConcept C200331156 @default.
• W3209367351 hasConcept C28826006 @default.
• W3209367351 hasConcept C2984842247 @default.
• W3209367351 hasConcept C33923547 @default.
• W3209367351 hasConcept C37736160 @default.
• W3209367351 hasConcept C41008148 @default.
• W3209367351 hasConcept C50644808 @default.
• W3209367351 hasConcept C62520636 @default.
• W3209367351 hasConceptScore W3209367351C11413529 @default.
• W3209367351 hasConceptScore W3209367351C121332964 @default.
• W3209367351 hasConceptScore W3209367351C154945302 @default.
• W3209367351 hasConceptScore W3209367351C177918212 @default.
• W3209367351 hasConceptScore W3209367351C200331156 @default.
• W3209367351 hasConceptScore W3209367351C28826006 @default.
• W3209367351 hasConceptScore W3209367351C2984842247 @default.
• W3209367351 hasConceptScore W3209367351C33923547 @default.
• W3209367351 hasConceptScore W3209367351C37736160 @default.
• W3209367351 hasConceptScore W3209367351C41008148 @default.
• W3209367351 hasConceptScore W3209367351C50644808 @default.
• W3209367351 hasConceptScore W3209367351C62520636 @default.
• W3209367351 hasIssue "7" @default.
• W3209367351 hasLocation W32093673511 @default.
• W3209367351 hasLocation W32093673512 @default.
• W3209367351 hasOpenAccess W3209367351 @default.
• W3209367351 hasPrimaryLocation W32093673511 @default.
• W3209367351 hasRelatedWork W2516574342 @default.
• W3209367351 hasRelatedWork W2791122243 @default.
• W3209367351 hasRelatedWork W2962821226 @default.
• W3209367351 hasRelatedWork W2996543462 @default.
• W3209367351 hasRelatedWork W3209367351 @default.
• W3209367351 hasRelatedWork W4288733390 @default.
• W3209367351 hasRelatedWork W4292518679 @default.
• W3209367351 hasRelatedWork W4312120836 @default.
• W3209367351 hasRelatedWork W4353115328 @default.
• W3209367351 hasRelatedWork W4287867272 @default.
• W3209367351 hasVolume "37" @default.
• W3209367351 isParatext "false" @default.
• W3209367351 isRetracted "false" @default.
• W3209367351 magId "3209367351" @default.
• W3209367351 workType "article" @default.