Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386822268> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4386822268 abstract "CNNs (Convolutional Neural Networks) have a good performance on most classification tasks, but they are vulnerable when meeting adversarial examples. Research and design of highly aggressive adversarial examples can help enhance the security and robustness of CNNs. The transferability of adversarial examples is still low in black-box settings. Therefore, an adversarial example method based on probability histogram equalization, namely HE-MI-FGSM (Histogram Equalization Momentum Iterative Fast Gradient Sign Method) is proposed. In each iteration of the adversarial example generation process, the original input image is randomly histogram equalized, and then the gradient is calculated to generate adversarial perturbations to mitigate overfitting in the adversarial example. The effectiveness of the method is verified on the ImageNet dataset. Compared with the advanced method I-FGSM (Iterative Fast Gradient Sign Method) and MI-FGSM (Momentum I-FGSM), the attack success rate in the adversarial training network increased by 27.9% and 7.7% on average, respectively." @default.
- W4386822268 created "2023-09-19" @default.
- W4386822268 creator A5005755579 @default.
- W4386822268 creator A5012558857 @default.
- W4386822268 creator A5016675782 @default.
- W4386822268 creator A5020941371 @default.
- W4386822268 date "2023-07-24" @default.
- W4386822268 modified "2023-10-16" @default.
- W4386822268 title "Adversarial Example Generation Method Based on Probability Histogram Equalization" @default.
- W4386822268 cites W2183341477 @default.
- W4386822268 cites W2302255633 @default.
- W4386822268 cites W2535873859 @default.
- W4386822268 cites W2618530766 @default.
- W4386822268 cites W2774644650 @default.
- W4386822268 cites W2798302089 @default.
- W4386822268 cites W2912250162 @default.
- W4386822268 cites W2962847335 @default.
- W4386822268 cites W2963542245 @default.
- W4386822268 cites W2963857521 @default.
- W4386822268 cites W2964350391 @default.
- W4386822268 cites W2969542116 @default.
- W4386822268 cites W3034176567 @default.
- W4386822268 cites W3159196909 @default.
- W4386822268 cites W4315705623 @default.
- W4386822268 cites W4320002812 @default.
- W4386822268 doi "https://doi.org/10.23919/ccc58697.2023.10240834" @default.
- W4386822268 hasPublicationYear "2023" @default.
- W4386822268 type Work @default.
- W4386822268 citedByCount "0" @default.
- W4386822268 crossrefType "proceedings-article" @default.
- W4386822268 hasAuthorship W4386822268A5005755579 @default.
- W4386822268 hasAuthorship W4386822268A5012558857 @default.
- W4386822268 hasAuthorship W4386822268A5016675782 @default.
- W4386822268 hasAuthorship W4386822268A5020941371 @default.
- W4386822268 hasConcept C11413529 @default.
- W4386822268 hasConcept C115961682 @default.
- W4386822268 hasConcept C119857082 @default.
- W4386822268 hasConcept C136943445 @default.
- W4386822268 hasConcept C140331021 @default.
- W4386822268 hasConcept C153180895 @default.
- W4386822268 hasConcept C154945302 @default.
- W4386822268 hasConcept C22019652 @default.
- W4386822268 hasConcept C30387639 @default.
- W4386822268 hasConcept C37736160 @default.
- W4386822268 hasConcept C41008148 @default.
- W4386822268 hasConcept C50644808 @default.
- W4386822268 hasConcept C53533937 @default.
- W4386822268 hasConcept C61272859 @default.
- W4386822268 hasConcept C81363708 @default.
- W4386822268 hasConceptScore W4386822268C11413529 @default.
- W4386822268 hasConceptScore W4386822268C115961682 @default.
- W4386822268 hasConceptScore W4386822268C119857082 @default.
- W4386822268 hasConceptScore W4386822268C136943445 @default.
- W4386822268 hasConceptScore W4386822268C140331021 @default.
- W4386822268 hasConceptScore W4386822268C153180895 @default.
- W4386822268 hasConceptScore W4386822268C154945302 @default.
- W4386822268 hasConceptScore W4386822268C22019652 @default.
- W4386822268 hasConceptScore W4386822268C30387639 @default.
- W4386822268 hasConceptScore W4386822268C37736160 @default.
- W4386822268 hasConceptScore W4386822268C41008148 @default.
- W4386822268 hasConceptScore W4386822268C50644808 @default.
- W4386822268 hasConceptScore W4386822268C53533937 @default.
- W4386822268 hasConceptScore W4386822268C61272859 @default.
- W4386822268 hasConceptScore W4386822268C81363708 @default.
- W4386822268 hasFunder F4320321001 @default.
- W4386822268 hasLocation W43868222681 @default.
- W4386822268 hasOpenAccess W4386822268 @default.
- W4386822268 hasPrimaryLocation W43868222681 @default.
- W4386822268 hasRelatedWork W1983610137 @default.
- W4386822268 hasRelatedWork W2057981026 @default.
- W4386822268 hasRelatedWork W2063599644 @default.
- W4386822268 hasRelatedWork W2136748848 @default.
- W4386822268 hasRelatedWork W2162593906 @default.
- W4386822268 hasRelatedWork W2256021896 @default.
- W4386822268 hasRelatedWork W2333844802 @default.
- W4386822268 hasRelatedWork W2385217229 @default.
- W4386822268 hasRelatedWork W2604503469 @default.
- W4386822268 hasRelatedWork W2767651786 @default.
- W4386822268 isParatext "false" @default.
- W4386822268 isRetracted "false" @default.
- W4386822268 workType "article" @default.