Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386433103> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4386433103 endingPage "344" @default.
- W4386433103 startingPage "332" @default.
- W4386433103 abstract "Deep learning (DL) models have demonstrated impressive performance in sensitive medical applications such as disease diagnosis. However, a backdoor attack embedded in the clean dataset without poisoning the labels poses a severe threat to the integrity of Artificial Intelligence (AI) technology. In literature, a lot of work has been done on backdoor attacks for medical applications, in which most of the authors assumed that the labels of the samples are also poisoned. This compromises the elusiveness of the backdoor attacks because poisoned samples can be identified by visual inspection by finding the mismatch between the labels of the samples. In this paper, an elusive backdoor attack is proposed, that makes the poisoned samples difficult to recognize. In the proposed approach a backdoor signal superimposed into a small portion of the clean dataset during training time is proposed. Moreover, this paper proposes a hybrid attack that further increases the Attack Success Rate (ASR). The proposed approach is evaluated over a Convolutional Neural Network (CNN)-based system for Magnetic Resonance Imaging (MRI) brain tumor classification, which demonstrated the effectiveness of the attacks, thus raising concern regarding using AI in sensitive applications." @default.
- W4386433103 created "2023-09-05" @default.
- W4386433103 creator A5030121038 @default.
- W4386433103 creator A5038672964 @default.
- W4386433103 creator A5080473845 @default.
- W4386433103 date "2023-01-01" @default.
- W4386433103 modified "2023-10-16" @default.
- W4386433103 title "BHAC-MRI: Backdoor and Hybrid Attacks on MRI Brain Tumor Classification Using CNN" @default.
- W4386433103 cites W2107397716 @default.
- W4386433103 cites W2293844262 @default.
- W4386433103 cites W2890430415 @default.
- W4386433103 cites W2970335439 @default.
- W4386433103 cites W3098772125 @default.
- W4386433103 cites W3107645027 @default.
- W4386433103 cites W3204634252 @default.
- W4386433103 cites W3205084690 @default.
- W4386433103 cites W4206244849 @default.
- W4386433103 cites W4224030674 @default.
- W4386433103 cites W4312280786 @default.
- W4386433103 doi "https://doi.org/10.1007/978-3-031-43153-1_28" @default.
- W4386433103 hasPublicationYear "2023" @default.
- W4386433103 type Work @default.
- W4386433103 citedByCount "0" @default.
- W4386433103 crossrefType "book-chapter" @default.
- W4386433103 hasAuthorship W4386433103A5030121038 @default.
- W4386433103 hasAuthorship W4386433103A5038672964 @default.
- W4386433103 hasAuthorship W4386433103A5080473845 @default.
- W4386433103 hasConcept C108583219 @default.
- W4386433103 hasConcept C119857082 @default.
- W4386433103 hasConcept C153180895 @default.
- W4386433103 hasConcept C154945302 @default.
- W4386433103 hasConcept C2781045450 @default.
- W4386433103 hasConcept C38652104 @default.
- W4386433103 hasConcept C41008148 @default.
- W4386433103 hasConcept C81363708 @default.
- W4386433103 hasConceptScore W4386433103C108583219 @default.
- W4386433103 hasConceptScore W4386433103C119857082 @default.
- W4386433103 hasConceptScore W4386433103C153180895 @default.
- W4386433103 hasConceptScore W4386433103C154945302 @default.
- W4386433103 hasConceptScore W4386433103C2781045450 @default.
- W4386433103 hasConceptScore W4386433103C38652104 @default.
- W4386433103 hasConceptScore W4386433103C41008148 @default.
- W4386433103 hasConceptScore W4386433103C81363708 @default.
- W4386433103 hasLocation W43864331031 @default.
- W4386433103 hasOpenAccess W4386433103 @default.
- W4386433103 hasPrimaryLocation W43864331031 @default.
- W4386433103 hasRelatedWork W2731899572 @default.
- W4386433103 hasRelatedWork W2999805992 @default.
- W4386433103 hasRelatedWork W3116150086 @default.
- W4386433103 hasRelatedWork W3133861977 @default.
- W4386433103 hasRelatedWork W4200173597 @default.
- W4386433103 hasRelatedWork W4223943233 @default.
- W4386433103 hasRelatedWork W4291897433 @default.
- W4386433103 hasRelatedWork W4312417841 @default.
- W4386433103 hasRelatedWork W4321369474 @default.
- W4386433103 hasRelatedWork W4380075502 @default.
- W4386433103 isParatext "false" @default.
- W4386433103 isRetracted "false" @default.
- W4386433103 workType "book-chapter" @default.