Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091490915> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3091490915 abstract "GAN (Generative Adversarial Networks, [1]) is a machine-learning-based generative approach, which can create artificial contents such as images, languages and speeches. Recent studies have shown that GAN can also be applied to generate adversarial attack examples ( [2], [3]) to fool the machine-learning models. In comparison with the non-learning adversarial attack examples approaches, the GAN-based adversarial attack example approach can generate the adversarial samples quickly when facing a new sample after training, but meanwhile needs to perturb the attack samples in great quantities. To address this issue, we propose a new approach, named Few-Features-Attack-GAN (FFA-GAN). FFA-GAN has a significant time-consuming advantage than the non-learning adversarial attack samples approaches as it is based on the GAN architecture, and also has a better non-zero-features performance than the GAN-based adversarial sample attack approaches because of the introduction of the mask mechanism in the generator of GAN to confine the perturbations. Experiments are made respectively on the structured data sets KDD-Cup 1999 and CIC-IDS 2017, in which the dimensions of the data are relatively low, and also on the unstructured data sets MNIST and CIFAR-10 in which the data have the relatively high dimensions. The results of the experiments demonstrate the effectiveness and the robustness of our proposed approach." @default.
- W3091490915 created "2020-10-08" @default.
- W3091490915 creator A5044869217 @default.
- W3091490915 creator A5068469832 @default.
- W3091490915 creator A5083563688 @default.
- W3091490915 creator A5087474264 @default.
- W3091490915 date "2020-07-01" @default.
- W3091490915 modified "2023-10-18" @default.
- W3091490915 title "Few Features Attack to Fool Machine Learning Models through Mask-based GAN" @default.
- W3091490915 cites W1686810756 @default.
- W3091490915 cites W1992222410 @default.
- W3091490915 cites W2099471712 @default.
- W3091490915 cites W2112796928 @default.
- W3091490915 cites W2125283600 @default.
- W3091490915 cites W2180612164 @default.
- W3091490915 cites W2194775991 @default.
- W3091490915 cites W2593414223 @default.
- W3091490915 cites W2739748921 @default.
- W3091490915 cites W2783555701 @default.
- W3091490915 cites W2789828921 @default.
- W3091490915 cites W2889836475 @default.
- W3091490915 cites W2963150697 @default.
- W3091490915 cites W2963207607 @default.
- W3091490915 cites W2963341071 @default.
- W3091490915 cites W2964153729 @default.
- W3091490915 cites W2964268978 @default.
- W3091490915 cites W3102476541 @default.
- W3091490915 cites W3103557498 @default.
- W3091490915 cites W3118608800 @default.
- W3091490915 doi "https://doi.org/10.1109/ijcnn48605.2020.9206922" @default.
- W3091490915 hasPublicationYear "2020" @default.
- W3091490915 type Work @default.
- W3091490915 sameAs 3091490915 @default.
- W3091490915 citedByCount "1" @default.
- W3091490915 countsByYear W30914909152020 @default.
- W3091490915 crossrefType "proceedings-article" @default.
- W3091490915 hasAuthorship W3091490915A5044869217 @default.
- W3091490915 hasAuthorship W3091490915A5068469832 @default.
- W3091490915 hasAuthorship W3091490915A5083563688 @default.
- W3091490915 hasAuthorship W3091490915A5087474264 @default.
- W3091490915 hasBestOaLocation W30914909152 @default.
- W3091490915 hasConcept C104317684 @default.
- W3091490915 hasConcept C108583219 @default.
- W3091490915 hasConcept C119857082 @default.
- W3091490915 hasConcept C121332964 @default.
- W3091490915 hasConcept C154945302 @default.
- W3091490915 hasConcept C163258240 @default.
- W3091490915 hasConcept C185592680 @default.
- W3091490915 hasConcept C190502265 @default.
- W3091490915 hasConcept C198531522 @default.
- W3091490915 hasConcept C2778403875 @default.
- W3091490915 hasConcept C2780992000 @default.
- W3091490915 hasConcept C2988773926 @default.
- W3091490915 hasConcept C37736160 @default.
- W3091490915 hasConcept C39890363 @default.
- W3091490915 hasConcept C41008148 @default.
- W3091490915 hasConcept C43617362 @default.
- W3091490915 hasConcept C55493867 @default.
- W3091490915 hasConcept C62520636 @default.
- W3091490915 hasConcept C63479239 @default.
- W3091490915 hasConceptScore W3091490915C104317684 @default.
- W3091490915 hasConceptScore W3091490915C108583219 @default.
- W3091490915 hasConceptScore W3091490915C119857082 @default.
- W3091490915 hasConceptScore W3091490915C121332964 @default.
- W3091490915 hasConceptScore W3091490915C154945302 @default.
- W3091490915 hasConceptScore W3091490915C163258240 @default.
- W3091490915 hasConceptScore W3091490915C185592680 @default.
- W3091490915 hasConceptScore W3091490915C190502265 @default.
- W3091490915 hasConceptScore W3091490915C198531522 @default.
- W3091490915 hasConceptScore W3091490915C2778403875 @default.
- W3091490915 hasConceptScore W3091490915C2780992000 @default.
- W3091490915 hasConceptScore W3091490915C2988773926 @default.
- W3091490915 hasConceptScore W3091490915C37736160 @default.
- W3091490915 hasConceptScore W3091490915C39890363 @default.
- W3091490915 hasConceptScore W3091490915C41008148 @default.
- W3091490915 hasConceptScore W3091490915C43617362 @default.
- W3091490915 hasConceptScore W3091490915C55493867 @default.
- W3091490915 hasConceptScore W3091490915C62520636 @default.
- W3091490915 hasConceptScore W3091490915C63479239 @default.
- W3091490915 hasLocation W30914909151 @default.
- W3091490915 hasLocation W30914909152 @default.
- W3091490915 hasOpenAccess W3091490915 @default.
- W3091490915 hasPrimaryLocation W30914909151 @default.
- W3091490915 hasRelatedWork W11738893 @default.
- W3091490915 hasRelatedWork W12219208 @default.
- W3091490915 hasRelatedWork W13683749 @default.
- W3091490915 hasRelatedWork W3891032 @default.
- W3091490915 hasRelatedWork W4703903 @default.
- W3091490915 hasRelatedWork W4972971 @default.
- W3091490915 hasRelatedWork W5470710 @default.
- W3091490915 hasRelatedWork W6908809 @default.
- W3091490915 hasRelatedWork W7619760 @default.
- W3091490915 hasRelatedWork W9657784 @default.
- W3091490915 isParatext "false" @default.
- W3091490915 isRetracted "false" @default.
- W3091490915 magId "3091490915" @default.
- W3091490915 workType "article" @default.