Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225525990> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4225525990 abstract "Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is adversarial training, which reaches a trade-off between robustness and generalization. This paper introduces a novel framework (Layer Sustainability Analysis (LSA)) for the analysis of layer vulnerability in an arbitrary neural network in the scenario of adversarial attacks. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversarial training approaches towards improving the sustainability of model layers via layer monitoring and analysis. The LSA framework identifies a list of Most Vulnerable Layers (MVL list) of the given network. The relative error, as a comparison measure, is used to evaluate representation sustainability of each layer against adversarial inputs. The proposed approach for obtaining robust neural networks to fend off adversarial attacks is based on a layer-wise regularization (LR) over LSA proposal(s) for adversarial training (AT); i.e. the AT-LR procedure. AT-LR could be used with any benchmark adversarial attack to reduce the vulnerability of network layers and to improve conventional adversarial training approaches. The proposed idea performs well theoretically and experimentally for state-of-the-art multilayer perceptron and convolutional neural network architectures. Compared with the AT-LR and its corresponding base adversarial training, the classification accuracy of more significant perturbations increased by 16.35%, 21.79%, and 10.730% on Moon, MNIST, and CIFAR-10 benchmark datasets, respectively. The LSA framework is available and published at https://github.com/khalooei/LSA." @default.
- W4225525990 created "2022-05-05" @default.
- W4225525990 creator A5006999765 @default.
- W4225525990 creator A5033765840 @default.
- W4225525990 creator A5048230415 @default.
- W4225525990 date "2022-02-05" @default.
- W4225525990 modified "2023-09-28" @default.
- W4225525990 title "Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework" @default.
- W4225525990 doi "https://doi.org/10.48550/arxiv.2202.02626" @default.
- W4225525990 hasPublicationYear "2022" @default.
- W4225525990 type Work @default.
- W4225525990 citedByCount "0" @default.
- W4225525990 crossrefType "posted-content" @default.
- W4225525990 hasAuthorship W4225525990A5006999765 @default.
- W4225525990 hasAuthorship W4225525990A5033765840 @default.
- W4225525990 hasAuthorship W4225525990A5048230415 @default.
- W4225525990 hasBestOaLocation W42255259901 @default.
- W4225525990 hasConcept C108583219 @default.
- W4225525990 hasConcept C119857082 @default.
- W4225525990 hasConcept C154945302 @default.
- W4225525990 hasConcept C190502265 @default.
- W4225525990 hasConcept C37736160 @default.
- W4225525990 hasConcept C41008148 @default.
- W4225525990 hasConcept C50644808 @default.
- W4225525990 hasConcept C60908668 @default.
- W4225525990 hasConcept C81363708 @default.
- W4225525990 hasConceptScore W4225525990C108583219 @default.
- W4225525990 hasConceptScore W4225525990C119857082 @default.
- W4225525990 hasConceptScore W4225525990C154945302 @default.
- W4225525990 hasConceptScore W4225525990C190502265 @default.
- W4225525990 hasConceptScore W4225525990C37736160 @default.
- W4225525990 hasConceptScore W4225525990C41008148 @default.
- W4225525990 hasConceptScore W4225525990C50644808 @default.
- W4225525990 hasConceptScore W4225525990C60908668 @default.
- W4225525990 hasConceptScore W4225525990C81363708 @default.
- W4225525990 hasLocation W42255259901 @default.
- W4225525990 hasOpenAccess W4225525990 @default.
- W4225525990 hasPrimaryLocation W42255259901 @default.
- W4225525990 hasRelatedWork W2248239756 @default.
- W4225525990 hasRelatedWork W2550787675 @default.
- W4225525990 hasRelatedWork W2597787948 @default.
- W4225525990 hasRelatedWork W2755956102 @default.
- W4225525990 hasRelatedWork W2799208032 @default.
- W4225525990 hasRelatedWork W2951786554 @default.
- W4225525990 hasRelatedWork W2978290780 @default.
- W4225525990 hasRelatedWork W4285586943 @default.
- W4225525990 hasRelatedWork W4287776258 @default.
- W4225525990 hasRelatedWork W4293350742 @default.
- W4225525990 isParatext "false" @default.
- W4225525990 isRetracted "false" @default.
- W4225525990 workType "article" @default.