Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297889740> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4297889740 abstract "Constructing adversarial perturbations for deep neural networks is an important direction of research. Crafting image-dependent adversarial perturbations using white-box feedback has hitherto been the norm for such adversarial attacks. However, black-box attacks are much more practical for real-world applications. Universal perturbations applicable across multiple images are gaining popularity due to their innate generalizability. There have also been efforts to restrict the perturbations to a few pixels in the image. This helps to retain visual similarity with the original images making such attacks hard to detect. This paper marks an important step which combines all these directions of research. We propose the DEceit algorithm for constructing effective universal pixel-restricted perturbations using only black-box feedback from the target network. We conduct empirical investigations using the ImageNet validation set on the state-of-the-art deep neural classifiers by varying the number of pixels to be perturbed from a meagre 10 pixels to as high as all pixels in the image. We find that perturbing only about 10% of the pixels in an image using DEceit achieves a commendable and highly transferable Fooling Rate while retaining the visual quality. We further demonstrate that DEceit can be successfully applied to image dependent attacks as well. In both sets of experiments, we outperformed several state-of-the-art methods." @default.
- W4297889740 created "2022-10-01" @default.
- W4297889740 creator A5000078546 @default.
- W4297889740 creator A5002653957 @default.
- W4297889740 creator A5043565079 @default.
- W4297889740 creator A5052826041 @default.
- W4297889740 creator A5076985884 @default.
- W4297889740 creator A5082982352 @default.
- W4297889740 date "2020-04-24" @default.
- W4297889740 modified "2023-10-16" @default.
- W4297889740 title "A Black-box Adversarial Attack Strategy with Adjustable Sparsity and Generalizability for Deep Image Classifiers" @default.
- W4297889740 doi "https://doi.org/10.48550/arxiv.2004.13002" @default.
- W4297889740 hasPublicationYear "2020" @default.
- W4297889740 type Work @default.
- W4297889740 citedByCount "0" @default.
- W4297889740 crossrefType "posted-content" @default.
- W4297889740 hasAuthorship W4297889740A5000078546 @default.
- W4297889740 hasAuthorship W4297889740A5002653957 @default.
- W4297889740 hasAuthorship W4297889740A5043565079 @default.
- W4297889740 hasAuthorship W4297889740A5052826041 @default.
- W4297889740 hasAuthorship W4297889740A5076985884 @default.
- W4297889740 hasAuthorship W4297889740A5082982352 @default.
- W4297889740 hasBestOaLocation W42978897401 @default.
- W4297889740 hasConcept C105795698 @default.
- W4297889740 hasConcept C108583219 @default.
- W4297889740 hasConcept C115961682 @default.
- W4297889740 hasConcept C153180895 @default.
- W4297889740 hasConcept C154945302 @default.
- W4297889740 hasConcept C160633673 @default.
- W4297889740 hasConcept C27158222 @default.
- W4297889740 hasConcept C2984842247 @default.
- W4297889740 hasConcept C31972630 @default.
- W4297889740 hasConcept C33923547 @default.
- W4297889740 hasConcept C37736160 @default.
- W4297889740 hasConcept C41008148 @default.
- W4297889740 hasConcept C50644808 @default.
- W4297889740 hasConcept C94966114 @default.
- W4297889740 hasConceptScore W4297889740C105795698 @default.
- W4297889740 hasConceptScore W4297889740C108583219 @default.
- W4297889740 hasConceptScore W4297889740C115961682 @default.
- W4297889740 hasConceptScore W4297889740C153180895 @default.
- W4297889740 hasConceptScore W4297889740C154945302 @default.
- W4297889740 hasConceptScore W4297889740C160633673 @default.
- W4297889740 hasConceptScore W4297889740C27158222 @default.
- W4297889740 hasConceptScore W4297889740C2984842247 @default.
- W4297889740 hasConceptScore W4297889740C31972630 @default.
- W4297889740 hasConceptScore W4297889740C33923547 @default.
- W4297889740 hasConceptScore W4297889740C37736160 @default.
- W4297889740 hasConceptScore W4297889740C41008148 @default.
- W4297889740 hasConceptScore W4297889740C50644808 @default.
- W4297889740 hasConceptScore W4297889740C94966114 @default.
- W4297889740 hasLocation W42978897401 @default.
- W4297889740 hasOpenAccess W4297889740 @default.
- W4297889740 hasPrimaryLocation W42978897401 @default.
- W4297889740 hasRelatedWork W2773120646 @default.
- W4297889740 hasRelatedWork W2897842727 @default.
- W4297889740 hasRelatedWork W2901671134 @default.
- W4297889740 hasRelatedWork W3002363318 @default.
- W4297889740 hasRelatedWork W3171219085 @default.
- W4297889740 hasRelatedWork W3195153428 @default.
- W4297889740 hasRelatedWork W3197603303 @default.
- W4297889740 hasRelatedWork W4225493432 @default.
- W4297889740 hasRelatedWork W4226180298 @default.
- W4297889740 hasRelatedWork W4297889740 @default.
- W4297889740 isParatext "false" @default.
- W4297889740 isRetracted "false" @default.
- W4297889740 workType "article" @default.