Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385654584> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4385654584 endingPage "288" @default.
- W4385654584 startingPage "276" @default.
- W4385654584 abstract "In practice, deep learning models are easy to be fooled by input images with subtle perturbations, and those images are called adversarial examples. Regarding one model, the crafted adversarial examples can successfully fool other models with varying architectures but the same task, which is referred to as adversarial transferability. Nevertheless, in practice, it is hard to get information about the model to be attacked, transfer-based adversarial attacks have developed rapidly. Later, different techniques are proposed to promote adversarial transferability. Different from existing input transformation attacks based on spatial transformation, our approach is a novel one on the basis of information deletion. By deleting squares of the input images by channels, we mitigate overfitting on the surrogate model of the adversarial examples and further enhance adversarial transferability. The corresponding performance of our method is superior to the existing input transformation attacks on different models (here, we consider unsecured models and defense ones), as demonstrated by extensive evaluations on ImageNet." @default.
- W4385654584 created "2023-08-09" @default.
- W4385654584 creator A5038915198 @default.
- W4385654584 creator A5047533842 @default.
- W4385654584 creator A5056120088 @default.
- W4385654584 creator A5056225848 @default.
- W4385654584 creator A5056815920 @default.
- W4385654584 date "2023-01-01" @default.
- W4385654584 modified "2023-09-24" @default.
- W4385654584 title "DBA: An Efficient Approach to Boost Transfer-Based Adversarial Attack Performance Through Information Deletion" @default.
- W4385654584 cites W2117539524 @default.
- W4385654584 cites W2183341477 @default.
- W4385654584 cites W2194775991 @default.
- W4385654584 cites W2302255633 @default.
- W4385654584 cites W2412782625 @default.
- W4385654584 cites W2774644650 @default.
- W4385654584 cites W2896078964 @default.
- W4385654584 cites W2962847335 @default.
- W4385654584 cites W2964350391 @default.
- W4385654584 cites W2969542116 @default.
- W4385654584 cites W3127807678 @default.
- W4385654584 cites W3186991201 @default.
- W4385654584 cites W4285817703 @default.
- W4385654584 cites W4290844250 @default.
- W4385654584 cites W4290935136 @default.
- W4385654584 cites W4312816015 @default.
- W4385654584 cites W4320717667 @default.
- W4385654584 cites W4366817438 @default.
- W4385654584 doi "https://doi.org/10.1007/978-3-031-40286-9_23" @default.
- W4385654584 hasPublicationYear "2023" @default.
- W4385654584 type Work @default.
- W4385654584 citedByCount "0" @default.
- W4385654584 crossrefType "book-chapter" @default.
- W4385654584 hasAuthorship W4385654584A5038915198 @default.
- W4385654584 hasAuthorship W4385654584A5047533842 @default.
- W4385654584 hasAuthorship W4385654584A5056120088 @default.
- W4385654584 hasAuthorship W4385654584A5056225848 @default.
- W4385654584 hasAuthorship W4385654584A5056815920 @default.
- W4385654584 hasConcept C104317684 @default.
- W4385654584 hasConcept C119857082 @default.
- W4385654584 hasConcept C140331021 @default.
- W4385654584 hasConcept C150899416 @default.
- W4385654584 hasConcept C154945302 @default.
- W4385654584 hasConcept C162324750 @default.
- W4385654584 hasConcept C185592680 @default.
- W4385654584 hasConcept C187736073 @default.
- W4385654584 hasConcept C204241405 @default.
- W4385654584 hasConcept C22019652 @default.
- W4385654584 hasConcept C2780451532 @default.
- W4385654584 hasConcept C37736160 @default.
- W4385654584 hasConcept C41008148 @default.
- W4385654584 hasConcept C50644808 @default.
- W4385654584 hasConcept C55493867 @default.
- W4385654584 hasConcept C61272859 @default.
- W4385654584 hasConceptScore W4385654584C104317684 @default.
- W4385654584 hasConceptScore W4385654584C119857082 @default.
- W4385654584 hasConceptScore W4385654584C140331021 @default.
- W4385654584 hasConceptScore W4385654584C150899416 @default.
- W4385654584 hasConceptScore W4385654584C154945302 @default.
- W4385654584 hasConceptScore W4385654584C162324750 @default.
- W4385654584 hasConceptScore W4385654584C185592680 @default.
- W4385654584 hasConceptScore W4385654584C187736073 @default.
- W4385654584 hasConceptScore W4385654584C204241405 @default.
- W4385654584 hasConceptScore W4385654584C22019652 @default.
- W4385654584 hasConceptScore W4385654584C2780451532 @default.
- W4385654584 hasConceptScore W4385654584C37736160 @default.
- W4385654584 hasConceptScore W4385654584C41008148 @default.
- W4385654584 hasConceptScore W4385654584C50644808 @default.
- W4385654584 hasConceptScore W4385654584C55493867 @default.
- W4385654584 hasConceptScore W4385654584C61272859 @default.
- W4385654584 hasLocation W43856545841 @default.
- W4385654584 hasOpenAccess W4385654584 @default.
- W4385654584 hasPrimaryLocation W43856545841 @default.
- W4385654584 hasRelatedWork W2901701333 @default.
- W4385654584 hasRelatedWork W2989932438 @default.
- W4385654584 hasRelatedWork W3099765033 @default.
- W4385654584 hasRelatedWork W3217492763 @default.
- W4385654584 hasRelatedWork W4221044115 @default.
- W4385654584 hasRelatedWork W4221147655 @default.
- W4385654584 hasRelatedWork W4283360871 @default.
- W4385654584 hasRelatedWork W4306177406 @default.
- W4385654584 hasRelatedWork W4309956221 @default.
- W4385654584 hasRelatedWork W4372260187 @default.
- W4385654584 isParatext "false" @default.
- W4385654584 isRetracted "false" @default.
- W4385654584 workType "book-chapter" @default.