Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313288879> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4313288879 abstract "In the field of artificial intelligence, neural network is one of the key technologies used for image classification and recognition. However, recent work has demonstrated that deep neural networks are easily attacked by adversarial examples to make misjudgments. Adversarial examples are almost indistin-guishable from normal examples and yet cannot be classified correctly by neural networks. The existence of adversarial examples is a major obstacle to the practical application and deployment of neural networks, so the research on adversarial defense algorithms is an important topic in the field of AI security. This paper proposes an adversarial example defense algorithm based on a triplet network and voting decision mechanism. Firstly, two neural networks with different structures are trained based on normal dataset. Secondly, the first network is fine-tuned using the adversarial examples generated by these two networks, resulting in a third neural network. Then, these three neural networks are used as sub-networks in parallel to construct a triplet network. Through adversarial training and differences in structures, the transferability of adversarial examples among the three sub-networks is weakened. Finally, the final classification result is obtained by majority voting, based on the parallel output results of the three sub-networks. Through the complementarity between these three sub-networks, the defense against adversarial examples is realized. The experimental results demonstrate the effectiveness of this algorithm." @default.
- W4313288879 created "2023-01-06" @default.
- W4313288879 creator A5027376502 @default.
- W4313288879 creator A5083407343 @default.
- W4313288879 creator A5085979706 @default.
- W4313288879 date "2022-10-28" @default.
- W4313288879 modified "2023-09-30" @default.
- W4313288879 title "An Adversarial Defense Algorithm Based on Triplet Network and Voting Decision" @default.
- W4313288879 cites W2243397390 @default.
- W4313288879 cites W2535873859 @default.
- W4313288879 cites W2607219512 @default.
- W4313288879 cites W2962933288 @default.
- W4313288879 cites W2963857521 @default.
- W4313288879 cites W2985970291 @default.
- W4313288879 cites W3100321043 @default.
- W4313288879 cites W3122061855 @default.
- W4313288879 cites W3212219596 @default.
- W4313288879 cites W4221139075 @default.
- W4313288879 cites W4221156702 @default.
- W4313288879 doi "https://doi.org/10.1109/icus55513.2022.9986996" @default.
- W4313288879 hasPublicationYear "2022" @default.
- W4313288879 type Work @default.
- W4313288879 citedByCount "0" @default.
- W4313288879 crossrefType "proceedings-article" @default.
- W4313288879 hasAuthorship W4313288879A5027376502 @default.
- W4313288879 hasAuthorship W4313288879A5083407343 @default.
- W4313288879 hasAuthorship W4313288879A5085979706 @default.
- W4313288879 hasConcept C105339364 @default.
- W4313288879 hasConcept C111919701 @default.
- W4313288879 hasConcept C11413529 @default.
- W4313288879 hasConcept C119857082 @default.
- W4313288879 hasConcept C140331021 @default.
- W4313288879 hasConcept C154945302 @default.
- W4313288879 hasConcept C17744445 @default.
- W4313288879 hasConcept C199539241 @default.
- W4313288879 hasConcept C202444582 @default.
- W4313288879 hasConcept C26517878 @default.
- W4313288879 hasConcept C2780801425 @default.
- W4313288879 hasConcept C31258907 @default.
- W4313288879 hasConcept C33923547 @default.
- W4313288879 hasConcept C37736160 @default.
- W4313288879 hasConcept C38652104 @default.
- W4313288879 hasConcept C41008148 @default.
- W4313288879 hasConcept C50644808 @default.
- W4313288879 hasConcept C520049643 @default.
- W4313288879 hasConcept C61272859 @default.
- W4313288879 hasConcept C94625758 @default.
- W4313288879 hasConcept C9652623 @default.
- W4313288879 hasConceptScore W4313288879C105339364 @default.
- W4313288879 hasConceptScore W4313288879C111919701 @default.
- W4313288879 hasConceptScore W4313288879C11413529 @default.
- W4313288879 hasConceptScore W4313288879C119857082 @default.
- W4313288879 hasConceptScore W4313288879C140331021 @default.
- W4313288879 hasConceptScore W4313288879C154945302 @default.
- W4313288879 hasConceptScore W4313288879C17744445 @default.
- W4313288879 hasConceptScore W4313288879C199539241 @default.
- W4313288879 hasConceptScore W4313288879C202444582 @default.
- W4313288879 hasConceptScore W4313288879C26517878 @default.
- W4313288879 hasConceptScore W4313288879C2780801425 @default.
- W4313288879 hasConceptScore W4313288879C31258907 @default.
- W4313288879 hasConceptScore W4313288879C33923547 @default.
- W4313288879 hasConceptScore W4313288879C37736160 @default.
- W4313288879 hasConceptScore W4313288879C38652104 @default.
- W4313288879 hasConceptScore W4313288879C41008148 @default.
- W4313288879 hasConceptScore W4313288879C50644808 @default.
- W4313288879 hasConceptScore W4313288879C520049643 @default.
- W4313288879 hasConceptScore W4313288879C61272859 @default.
- W4313288879 hasConceptScore W4313288879C94625758 @default.
- W4313288879 hasConceptScore W4313288879C9652623 @default.
- W4313288879 hasLocation W43132888791 @default.
- W4313288879 hasOpenAccess W4313288879 @default.
- W4313288879 hasPrimaryLocation W43132888791 @default.
- W4313288879 hasRelatedWork W2914158293 @default.
- W4313288879 hasRelatedWork W2997056298 @default.
- W4313288879 hasRelatedWork W3092178728 @default.
- W4313288879 hasRelatedWork W3132910851 @default.
- W4313288879 hasRelatedWork W3137894200 @default.
- W4313288879 hasRelatedWork W4200630034 @default.
- W4313288879 hasRelatedWork W4226402597 @default.
- W4313288879 hasRelatedWork W4283325551 @default.
- W4313288879 hasRelatedWork W4288055406 @default.
- W4313288879 hasRelatedWork W4377864639 @default.
- W4313288879 isParatext "false" @default.
- W4313288879 isRetracted "false" @default.
- W4313288879 workType "article" @default.