Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387090147> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4387090147 abstract "Artificial intelligence technology represented by deep learning has been widely used in the real world, and its security has elicited increasing interest. Recent studies have shown that compared to white-box attacks, black-box adversarial attacks pose more serious security threats to deep neural networks. Therefore, evaluating model robustness by studying black-box adversarial attacks has become a research hotspot in the field of deep learning security. However, the existing adversarial attack methods generally suffer from the conflict between attack strength and imperceptibility. To solve this problem, this paper explores adversarial samples that are more in line with human perception of the more transferable intermediate layer features and proposes an intermediate layer adversarial attack algorithm stFA based on pixel spatial transformation. The proposed stFA promotes the model to misclassify adversarial samples as target labels, while encouraging the intermediate-layer feature representation of clean images to move away from the original labels. Extensive experiments have shown that stFA has both perfect imperceptibility and black-box transferability, which improves the success rate of targeted and untargeted attacks by 7.8% and 4.4% compared to stAdv." @default.
- W4387090147 created "2023-09-28" @default.
- W4387090147 creator A5030921116 @default.
- W4387090147 creator A5048936753 @default.
- W4387090147 creator A5054075262 @default.
- W4387090147 creator A5060773798 @default.
- W4387090147 creator A5066589468 @default.
- W4387090147 date "2023-07-07" @default.
- W4387090147 modified "2023-09-28" @default.
- W4387090147 title "A Transferable Adversarial Attack Algorithm Based On Spatial Transformation" @default.
- W4387090147 cites W2180612164 @default.
- W4387090147 cites W2183341477 @default.
- W4387090147 cites W2348664362 @default.
- W4387090147 cites W2618530766 @default.
- W4387090147 cites W2774644650 @default.
- W4387090147 cites W2798581339 @default.
- W4387090147 cites W2947874337 @default.
- W4387090147 cites W2953834312 @default.
- W4387090147 cites W2962785568 @default.
- W4387090147 cites W2962847335 @default.
- W4387090147 cites W2963428752 @default.
- W4387090147 cites W2963542245 @default.
- W4387090147 cites W2964350391 @default.
- W4387090147 cites W2984699060 @default.
- W4387090147 cites W2991496458 @default.
- W4387090147 cites W3034176567 @default.
- W4387090147 cites W3034619610 @default.
- W4387090147 cites W3111709374 @default.
- W4387090147 cites W3186991201 @default.
- W4387090147 cites W4221041279 @default.
- W4387090147 cites W4293011327 @default.
- W4387090147 cites W4313349685 @default.
- W4387090147 cites W4313532597 @default.
- W4387090147 cites W4315498026 @default.
- W4387090147 doi "https://doi.org/10.1109/bdai59165.2023.10256820" @default.
- W4387090147 hasPublicationYear "2023" @default.
- W4387090147 type Work @default.
- W4387090147 citedByCount "0" @default.
- W4387090147 crossrefType "proceedings-article" @default.
- W4387090147 hasAuthorship W4387090147A5030921116 @default.
- W4387090147 hasAuthorship W4387090147A5048936753 @default.
- W4387090147 hasAuthorship W4387090147A5054075262 @default.
- W4387090147 hasAuthorship W4387090147A5060773798 @default.
- W4387090147 hasAuthorship W4387090147A5066589468 @default.
- W4387090147 hasConcept C104317684 @default.
- W4387090147 hasConcept C108583219 @default.
- W4387090147 hasConcept C11413529 @default.
- W4387090147 hasConcept C119857082 @default.
- W4387090147 hasConcept C140331021 @default.
- W4387090147 hasConcept C153180895 @default.
- W4387090147 hasConcept C154945302 @default.
- W4387090147 hasConcept C185592680 @default.
- W4387090147 hasConcept C2984842247 @default.
- W4387090147 hasConcept C37736160 @default.
- W4387090147 hasConcept C38652104 @default.
- W4387090147 hasConcept C41008148 @default.
- W4387090147 hasConcept C55493867 @default.
- W4387090147 hasConcept C61272859 @default.
- W4387090147 hasConcept C63479239 @default.
- W4387090147 hasConcept C94966114 @default.
- W4387090147 hasConceptScore W4387090147C104317684 @default.
- W4387090147 hasConceptScore W4387090147C108583219 @default.
- W4387090147 hasConceptScore W4387090147C11413529 @default.
- W4387090147 hasConceptScore W4387090147C119857082 @default.
- W4387090147 hasConceptScore W4387090147C140331021 @default.
- W4387090147 hasConceptScore W4387090147C153180895 @default.
- W4387090147 hasConceptScore W4387090147C154945302 @default.
- W4387090147 hasConceptScore W4387090147C185592680 @default.
- W4387090147 hasConceptScore W4387090147C2984842247 @default.
- W4387090147 hasConceptScore W4387090147C37736160 @default.
- W4387090147 hasConceptScore W4387090147C38652104 @default.
- W4387090147 hasConceptScore W4387090147C41008148 @default.
- W4387090147 hasConceptScore W4387090147C55493867 @default.
- W4387090147 hasConceptScore W4387090147C61272859 @default.
- W4387090147 hasConceptScore W4387090147C63479239 @default.
- W4387090147 hasConceptScore W4387090147C94966114 @default.
- W4387090147 hasLocation W43870901471 @default.
- W4387090147 hasOpenAccess W4387090147 @default.
- W4387090147 hasPrimaryLocation W43870901471 @default.
- W4387090147 hasRelatedWork W2914158293 @default.
- W4387090147 hasRelatedWork W2950864148 @default.
- W4387090147 hasRelatedWork W3009622996 @default.
- W4387090147 hasRelatedWork W3093871791 @default.
- W4387090147 hasRelatedWork W3185166384 @default.
- W4387090147 hasRelatedWork W3193857078 @default.
- W4387090147 hasRelatedWork W3208304128 @default.
- W4387090147 hasRelatedWork W4213093132 @default.
- W4387090147 hasRelatedWork W4225493432 @default.
- W4387090147 hasRelatedWork W4366256806 @default.
- W4387090147 isParatext "false" @default.
- W4387090147 isRetracted "false" @default.
- W4387090147 workType "article" @default.