Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304762076> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4304762076 endingPage "2545" @default.
- W4304762076 startingPage "2545" @default.
- W4304762076 abstract "In the past years, deep neural networks (DNNs) have become popular in many disciplines such as computer vision (CV). One of the most important challenges in the CV area is Medical Image Analysis (MIA). However, adversarial attacks (AdAs) have proven to be an important threat to vision systems by significantly reducing the performance of the models. This paper proposes a new black-box adversarial attack, which is based οn orthogonal image moments named Mb-AdA. Additionally, a corresponding defensive method of adversarial training using Mb-AdA adversarial examples is also investigated, with encouraging results. The proposed attack was applied in classification and segmentation tasks with six state-of-the-art Deep Learning (DL) models in X-ray, histopathology and nuclei cell images. The main advantage of Mb-AdA is that it does not destroy the structure of images like other attacks, as instead of adding noise it removes specific image information, which is critical for medical models' decisions. The proposed attack is more effective than compared ones and achieved degradation up to 65% and 18% in terms of accuracy and IoU for classification and segmentation tasks, respectively, by also presenting relatively high SSIM. At the same time, it was proved that Mb-AdA adversarial examples can enhance the robustness of the model." @default.
- W4304762076 created "2022-10-13" @default.
- W4304762076 creator A5032725664 @default.
- W4304762076 creator A5067398723 @default.
- W4304762076 creator A5091279911 @default.
- W4304762076 date "2022-10-12" @default.
- W4304762076 modified "2023-10-01" @default.
- W4304762076 title "How Resilient Are Deep Learning Models in Medical Image Analysis? The Case of the Moment-Based Adversarial Attack (Mb-AdA)" @default.
- W4304762076 cites W2133665775 @default.
- W4304762076 cites W2159498975 @default.
- W4304762076 cites W2622826443 @default.
- W4304762076 cites W2807189427 @default.
- W4304762076 cites W2884367402 @default.
- W4304762076 cites W2885824038 @default.
- W4304762076 cites W2919115771 @default.
- W4304762076 cites W2944990428 @default.
- W4304762076 cites W2962858109 @default.
- W4304762076 cites W2964350391 @default.
- W4304762076 cites W2983683123 @default.
- W4304762076 cites W3013277995 @default.
- W4304762076 cites W3021182036 @default.
- W4304762076 cites W3026309613 @default.
- W4304762076 cites W3082954719 @default.
- W4304762076 cites W3096281486 @default.
- W4304762076 cites W3105300716 @default.
- W4304762076 cites W3107451140 @default.
- W4304762076 cites W3107645027 @default.
- W4304762076 cites W3198324776 @default.
- W4304762076 cites W4206693420 @default.
- W4304762076 cites W4297148103 @default.
- W4304762076 doi "https://doi.org/10.3390/biomedicines10102545" @default.
- W4304762076 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36289807" @default.
- W4304762076 hasPublicationYear "2022" @default.
- W4304762076 type Work @default.
- W4304762076 citedByCount "2" @default.
- W4304762076 countsByYear W43047620762023 @default.
- W4304762076 crossrefType "journal-article" @default.
- W4304762076 hasAuthorship W4304762076A5032725664 @default.
- W4304762076 hasAuthorship W4304762076A5067398723 @default.
- W4304762076 hasAuthorship W4304762076A5091279911 @default.
- W4304762076 hasBestOaLocation W43047620761 @default.
- W4304762076 hasConcept C104317684 @default.
- W4304762076 hasConcept C108583219 @default.
- W4304762076 hasConcept C115961682 @default.
- W4304762076 hasConcept C119857082 @default.
- W4304762076 hasConcept C121332964 @default.
- W4304762076 hasConcept C153180895 @default.
- W4304762076 hasConcept C154945302 @default.
- W4304762076 hasConcept C179254644 @default.
- W4304762076 hasConcept C185592680 @default.
- W4304762076 hasConcept C2984842247 @default.
- W4304762076 hasConcept C37736160 @default.
- W4304762076 hasConcept C41008148 @default.
- W4304762076 hasConcept C50644808 @default.
- W4304762076 hasConcept C55493867 @default.
- W4304762076 hasConcept C63479239 @default.
- W4304762076 hasConcept C74650414 @default.
- W4304762076 hasConcept C89600930 @default.
- W4304762076 hasConcept C94966114 @default.
- W4304762076 hasConceptScore W4304762076C104317684 @default.
- W4304762076 hasConceptScore W4304762076C108583219 @default.
- W4304762076 hasConceptScore W4304762076C115961682 @default.
- W4304762076 hasConceptScore W4304762076C119857082 @default.
- W4304762076 hasConceptScore W4304762076C121332964 @default.
- W4304762076 hasConceptScore W4304762076C153180895 @default.
- W4304762076 hasConceptScore W4304762076C154945302 @default.
- W4304762076 hasConceptScore W4304762076C179254644 @default.
- W4304762076 hasConceptScore W4304762076C185592680 @default.
- W4304762076 hasConceptScore W4304762076C2984842247 @default.
- W4304762076 hasConceptScore W4304762076C37736160 @default.
- W4304762076 hasConceptScore W4304762076C41008148 @default.
- W4304762076 hasConceptScore W4304762076C50644808 @default.
- W4304762076 hasConceptScore W4304762076C55493867 @default.
- W4304762076 hasConceptScore W4304762076C63479239 @default.
- W4304762076 hasConceptScore W4304762076C74650414 @default.
- W4304762076 hasConceptScore W4304762076C89600930 @default.
- W4304762076 hasConceptScore W4304762076C94966114 @default.
- W4304762076 hasIssue "10" @default.
- W4304762076 hasLocation W43047620761 @default.
- W4304762076 hasLocation W43047620762 @default.
- W4304762076 hasLocation W43047620763 @default.
- W4304762076 hasLocation W43047620764 @default.
- W4304762076 hasOpenAccess W4304762076 @default.
- W4304762076 hasPrimaryLocation W43047620761 @default.
- W4304762076 hasRelatedWork W2897842727 @default.
- W4304762076 hasRelatedWork W2963115223 @default.
- W4304762076 hasRelatedWork W3193857078 @default.
- W4304762076 hasRelatedWork W3208304128 @default.
- W4304762076 hasRelatedWork W3208723233 @default.
- W4304762076 hasRelatedWork W4225493432 @default.
- W4304762076 hasRelatedWork W4311734044 @default.
- W4304762076 hasRelatedWork W4320076403 @default.
- W4304762076 hasRelatedWork W4379255972 @default.
- W4304762076 hasRelatedWork W4286890323 @default.
- W4304762076 hasVolume "10" @default.
- W4304762076 isParatext "false" @default.
- W4304762076 isRetracted "false" @default.
- W4304762076 workType "article" @default.