Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387494391> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4387494391 endingPage "4236" @default.
- W4387494391 startingPage "4236" @default.
- W4387494391 abstract "With the emergence of COVID-19 disease in 2019, machine learning (ML) techniques, specifically deep learning networks (DNNs), played a key role in diagnosing the disease in the medical industry due to their superior performance. However, the computational cost of deep learning networks (DNNs) can be quite high, making it necessary to often outsource the training process to third-party providers, such as machine learning as a service (MLaaS). Therefore, careful consideration is required to achieve robustness in DNN-based systems against cyber-security attacks. In this paper, we propose a method called the dropout-bagging (DB-COVIDNet) algorithm, which works as a robust defense mechanism against poisoning backdoor attacks. In this model, the trigger-related features will be removed by the modified dropout algorithm, and then we will use the new voting method in the bagging algorithm to achieve the final results. We considered AC-COVIDNet as the main inducer of the bagging algorithm, which is an attention-guided contrastive convolutional neural network (CNN), and evaluated the performance of the proposed method with the malicious COVIDx dataset. The results demonstrated that DB-COVIDNet has strong robustness and can significantly reduce the effect of the backdoor attack. The proposed DB-COVIDNet nullifies backdoors before the attack has been activated, resulting in a tremendous reduction in the attack success rate from 99.5% to 3% with high accuracy on the clean data." @default.
- W4387494391 created "2023-10-11" @default.
- W4387494391 creator A5038419298 @default.
- W4387494391 creator A5054656260 @default.
- W4387494391 creator A5064247136 @default.
- W4387494391 date "2023-10-10" @default.
- W4387494391 modified "2023-10-12" @default.
- W4387494391 title "DB-COVIDNet: A Defense Method against Backdoor Attacks" @default.
- W4387494391 cites W2007339694 @default.
- W4387494391 cites W2074598933 @default.
- W4387494391 cites W2089093251 @default.
- W4387494391 cites W2108598243 @default.
- W4387494391 cites W2180612164 @default.
- W4387494391 cites W2194775991 @default.
- W4387494391 cites W2293768274 @default.
- W4387494391 cites W2543927648 @default.
- W4387494391 cites W2604319603 @default.
- W4387494391 cites W2753783305 @default.
- W4387494391 cites W2922073769 @default.
- W4387494391 cites W2934843808 @default.
- W4387494391 cites W2986013765 @default.
- W4387494391 cites W2990270730 @default.
- W4387494391 cites W3013277995 @default.
- W4387494391 cites W3020653337 @default.
- W4387494391 cites W3028201343 @default.
- W4387494391 cites W3037662149 @default.
- W4387494391 cites W3047095708 @default.
- W4387494391 cites W3090750097 @default.
- W4387494391 cites W3096918659 @default.
- W4387494391 cites W3105081694 @default.
- W4387494391 cites W3108080245 @default.
- W4387494391 cites W3120506007 @default.
- W4387494391 cites W3127596160 @default.
- W4387494391 cites W3136378322 @default.
- W4387494391 cites W3156317482 @default.
- W4387494391 cites W3164472293 @default.
- W4387494391 cites W3164820705 @default.
- W4387494391 cites W3191993634 @default.
- W4387494391 cites W3205084690 @default.
- W4387494391 cites W3209733456 @default.
- W4387494391 cites W3211185929 @default.
- W4387494391 cites W4212883601 @default.
- W4387494391 cites W4221005825 @default.
- W4387494391 cites W4252979261 @default.
- W4387494391 cites W4304945145 @default.
- W4387494391 cites W4313404355 @default.
- W4387494391 doi "https://doi.org/10.3390/math11204236" @default.
- W4387494391 hasPublicationYear "2023" @default.
- W4387494391 type Work @default.
- W4387494391 citedByCount "0" @default.
- W4387494391 crossrefType "journal-article" @default.
- W4387494391 hasAuthorship W4387494391A5038419298 @default.
- W4387494391 hasAuthorship W4387494391A5054656260 @default.
- W4387494391 hasAuthorship W4387494391A5064247136 @default.
- W4387494391 hasBestOaLocation W43874943911 @default.
- W4387494391 hasConcept C104317684 @default.
- W4387494391 hasConcept C108583219 @default.
- W4387494391 hasConcept C119857082 @default.
- W4387494391 hasConcept C154945302 @default.
- W4387494391 hasConcept C185592680 @default.
- W4387494391 hasConcept C2781045450 @default.
- W4387494391 hasConcept C2984842247 @default.
- W4387494391 hasConcept C38652104 @default.
- W4387494391 hasConcept C41008148 @default.
- W4387494391 hasConcept C55493867 @default.
- W4387494391 hasConcept C63479239 @default.
- W4387494391 hasConcept C81363708 @default.
- W4387494391 hasConceptScore W4387494391C104317684 @default.
- W4387494391 hasConceptScore W4387494391C108583219 @default.
- W4387494391 hasConceptScore W4387494391C119857082 @default.
- W4387494391 hasConceptScore W4387494391C154945302 @default.
- W4387494391 hasConceptScore W4387494391C185592680 @default.
- W4387494391 hasConceptScore W4387494391C2781045450 @default.
- W4387494391 hasConceptScore W4387494391C2984842247 @default.
- W4387494391 hasConceptScore W4387494391C38652104 @default.
- W4387494391 hasConceptScore W4387494391C41008148 @default.
- W4387494391 hasConceptScore W4387494391C55493867 @default.
- W4387494391 hasConceptScore W4387494391C63479239 @default.
- W4387494391 hasConceptScore W4387494391C81363708 @default.
- W4387494391 hasFunder F4320335199 @default.
- W4387494391 hasIssue "20" @default.
- W4387494391 hasLocation W43874943911 @default.
- W4387494391 hasOpenAccess W4387494391 @default.
- W4387494391 hasPrimaryLocation W43874943911 @default.
- W4387494391 hasRelatedWork W2951988008 @default.
- W4387494391 hasRelatedWork W2970990331 @default.
- W4387494391 hasRelatedWork W3029198973 @default.
- W4387494391 hasRelatedWork W3133861977 @default.
- W4387494391 hasRelatedWork W3167935049 @default.
- W4387494391 hasRelatedWork W3193565141 @default.
- W4387494391 hasRelatedWork W3210882018 @default.
- W4387494391 hasRelatedWork W4226493464 @default.
- W4387494391 hasRelatedWork W4312417841 @default.
- W4387494391 hasRelatedWork W4379116102 @default.
- W4387494391 hasVolume "11" @default.
- W4387494391 isParatext "false" @default.
- W4387494391 isRetracted "false" @default.
- W4387494391 workType "article" @default.