Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313251387> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4313251387 endingPage "1477" @default.
- W4313251387 startingPage "1464" @default.
- W4313251387 abstract "Abstract Image recognition on deep neural network is vulnerable to adversarial sample attacks. The adversarial attack accuracy is low when only limited queries on the target are allowed with the current black box environment. This paper proposes a target adversarial attack algorithm discrete cosine transform‐mean target feature attack (DTFA) based on the target features and a limited‐area sampling method. The algorithm first examines the original image and a target image to generate an initial adversarial example. Then the disturbance is sampled from the low‐frequency region intercepted by Gaussian noise after discrete cosine transform. The authors determine the size of the disturbance according to the difference between the adversarial example and the original image with consideration of the number of iterations and the position of the target feature region. The disturbance is applied on the initial adversarial example to generate the new adversarial example with the difference from the original image reduced. To evaluate the proposed algorithm, based on the common image classification model InceptionV3, and with identical queries accessing the same target model, the authors conduct experiments to compare the attack effectiveness of DTFA and the benchmark algorithms on the same image and target datasets. Experimental results show that the generated adversarial examples by the proposed algorithm are superior to 94% of those by the similar attack algorithms with less than 10,000 access queries on the target model." @default.
- W4313251387 created "2023-01-06" @default.
- W4313251387 creator A5017541508 @default.
- W4313251387 creator A5027008266 @default.
- W4313251387 creator A5028539723 @default.
- W4313251387 date "2022-12-27" @default.
- W4313251387 modified "2023-10-14" @default.
- W4313251387 title "DTFA: Adversarial attack with discrete cosine transform noise and target features on deep neural networks" @default.
- W4313251387 cites W2031614119 @default.
- W4313251387 cites W2183341477 @default.
- W4313251387 cites W2295107390 @default.
- W4313251387 cites W2603766943 @default.
- W4313251387 cites W2746600820 @default.
- W4313251387 cites W2887603965 @default.
- W4313251387 cites W2895097814 @default.
- W4313251387 cites W2962858109 @default.
- W4313251387 cites W2963178695 @default.
- W4313251387 cites W2963857521 @default.
- W4313251387 cites W2964205597 @default.
- W4313251387 cites W2997079108 @default.
- W4313251387 cites W3015625436 @default.
- W4313251387 cites W3108072218 @default.
- W4313251387 cites W4294310809 @default.
- W4313251387 cites W4296340047 @default.
- W4313251387 doi "https://doi.org/10.1049/ipr2.12727" @default.
- W4313251387 hasPublicationYear "2022" @default.
- W4313251387 type Work @default.
- W4313251387 citedByCount "0" @default.
- W4313251387 crossrefType "journal-article" @default.
- W4313251387 hasAuthorship W4313251387A5017541508 @default.
- W4313251387 hasAuthorship W4313251387A5027008266 @default.
- W4313251387 hasAuthorship W4313251387A5028539723 @default.
- W4313251387 hasBestOaLocation W43132513871 @default.
- W4313251387 hasConcept C11413529 @default.
- W4313251387 hasConcept C115961682 @default.
- W4313251387 hasConcept C13280743 @default.
- W4313251387 hasConcept C138885662 @default.
- W4313251387 hasConcept C153180895 @default.
- W4313251387 hasConcept C154945302 @default.
- W4313251387 hasConcept C185798385 @default.
- W4313251387 hasConcept C205649164 @default.
- W4313251387 hasConcept C2221639 @default.
- W4313251387 hasConcept C2776401178 @default.
- W4313251387 hasConcept C37736160 @default.
- W4313251387 hasConcept C41008148 @default.
- W4313251387 hasConcept C41895202 @default.
- W4313251387 hasConcept C50644808 @default.
- W4313251387 hasConcept C99498987 @default.
- W4313251387 hasConceptScore W4313251387C11413529 @default.
- W4313251387 hasConceptScore W4313251387C115961682 @default.
- W4313251387 hasConceptScore W4313251387C13280743 @default.
- W4313251387 hasConceptScore W4313251387C138885662 @default.
- W4313251387 hasConceptScore W4313251387C153180895 @default.
- W4313251387 hasConceptScore W4313251387C154945302 @default.
- W4313251387 hasConceptScore W4313251387C185798385 @default.
- W4313251387 hasConceptScore W4313251387C205649164 @default.
- W4313251387 hasConceptScore W4313251387C2221639 @default.
- W4313251387 hasConceptScore W4313251387C2776401178 @default.
- W4313251387 hasConceptScore W4313251387C37736160 @default.
- W4313251387 hasConceptScore W4313251387C41008148 @default.
- W4313251387 hasConceptScore W4313251387C41895202 @default.
- W4313251387 hasConceptScore W4313251387C50644808 @default.
- W4313251387 hasConceptScore W4313251387C99498987 @default.
- W4313251387 hasFunder F4320321001 @default.
- W4313251387 hasIssue "5" @default.
- W4313251387 hasLocation W43132513871 @default.
- W4313251387 hasOpenAccess W4313251387 @default.
- W4313251387 hasPrimaryLocation W43132513871 @default.
- W4313251387 hasRelatedWork W1485630101 @default.
- W4313251387 hasRelatedWork W1556544299 @default.
- W4313251387 hasRelatedWork W1591194399 @default.
- W4313251387 hasRelatedWork W2167423507 @default.
- W4313251387 hasRelatedWork W2382607599 @default.
- W4313251387 hasRelatedWork W2546942002 @default.
- W4313251387 hasRelatedWork W2737075200 @default.
- W4313251387 hasRelatedWork W2970216048 @default.
- W4313251387 hasRelatedWork W2978289231 @default.
- W4313251387 hasRelatedWork W4367598285 @default.
- W4313251387 hasVolume "17" @default.
- W4313251387 isParatext "false" @default.
- W4313251387 isRetracted "false" @default.
- W4313251387 workType "article" @default.