Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387303493> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4387303493 abstract "In recent years, the robustness of graph neural networks (GNNs) adversarial attacks has been favored by researchers, and related research has intensified. However, existing graph adversarial attacks are mainly performed by modifying the topology of the graph and node feature vectors, and attacks from the labels of nodes are rarely considered, especially for multi-label graph adversarial attacks, where an attacker can manipulate an obscure portion of the training labels and flip the sample labels in the training data to other classes, resulting in incorrect predictions of the retrained GNNs model. In this work, we present graph adversarial attack against multi-label flipping. We propose an effective attack model-Lapa, based on an adaptive genetic algorithm that searches the solution space for suitable adversarial samples to obtain near-optimal solutions. The adaptive genetic algorithm performs crossover and mutation operations utilizing adaptive probabilities. We demonstrate the effectiveness of our proposed Lapa attack model on GNNs after extensive experiments on four real datasets." @default.
- W4387303493 created "2023-10-04" @default.
- W4387303493 creator A5006794114 @default.
- W4387303493 creator A5014646620 @default.
- W4387303493 creator A5020055061 @default.
- W4387303493 creator A5090949378 @default.
- W4387303493 date "2023-04-01" @default.
- W4387303493 modified "2023-10-06" @default.
- W4387303493 title "Lapa: Multi-Label-Flipping Adversarial Attacks on Graph Neural Networks" @default.
- W4387303493 cites W2914317637 @default.
- W4387303493 cites W2964971928 @default.
- W4387303493 cites W2994598354 @default.
- W4387303493 cites W2997371401 @default.
- W4387303493 cites W3013520104 @default.
- W4387303493 cites W3097300053 @default.
- W4387303493 cites W3120491054 @default.
- W4387303493 cites W3127927415 @default.
- W4387303493 cites W3162648546 @default.
- W4387303493 cites W4210257598 @default.
- W4387303493 doi "https://doi.org/10.1109/scset58950.2023.00016" @default.
- W4387303493 hasPublicationYear "2023" @default.
- W4387303493 type Work @default.
- W4387303493 citedByCount "0" @default.
- W4387303493 crossrefType "proceedings-article" @default.
- W4387303493 hasAuthorship W4387303493A5006794114 @default.
- W4387303493 hasAuthorship W4387303493A5014646620 @default.
- W4387303493 hasAuthorship W4387303493A5020055061 @default.
- W4387303493 hasAuthorship W4387303493A5090949378 @default.
- W4387303493 hasConcept C104317684 @default.
- W4387303493 hasConcept C122507166 @default.
- W4387303493 hasConcept C132525143 @default.
- W4387303493 hasConcept C154945302 @default.
- W4387303493 hasConcept C185592680 @default.
- W4387303493 hasConcept C37736160 @default.
- W4387303493 hasConcept C41008148 @default.
- W4387303493 hasConcept C55493867 @default.
- W4387303493 hasConcept C63479239 @default.
- W4387303493 hasConcept C80444323 @default.
- W4387303493 hasConceptScore W4387303493C104317684 @default.
- W4387303493 hasConceptScore W4387303493C122507166 @default.
- W4387303493 hasConceptScore W4387303493C132525143 @default.
- W4387303493 hasConceptScore W4387303493C154945302 @default.
- W4387303493 hasConceptScore W4387303493C185592680 @default.
- W4387303493 hasConceptScore W4387303493C37736160 @default.
- W4387303493 hasConceptScore W4387303493C41008148 @default.
- W4387303493 hasConceptScore W4387303493C55493867 @default.
- W4387303493 hasConceptScore W4387303493C63479239 @default.
- W4387303493 hasConceptScore W4387303493C80444323 @default.
- W4387303493 hasLocation W43873034931 @default.
- W4387303493 hasOpenAccess W4387303493 @default.
- W4387303493 hasPrimaryLocation W43873034931 @default.
- W4387303493 hasRelatedWork W1943663474 @default.
- W4387303493 hasRelatedWork W2110294633 @default.
- W4387303493 hasRelatedWork W2306830238 @default.
- W4387303493 hasRelatedWork W2347477706 @default.
- W4387303493 hasRelatedWork W2482350142 @default.
- W4387303493 hasRelatedWork W2502115930 @default.
- W4387303493 hasRelatedWork W3126451824 @default.
- W4387303493 hasRelatedWork W3176240006 @default.
- W4387303493 hasRelatedWork W4246396837 @default.
- W4387303493 hasRelatedWork W4299389082 @default.
- W4387303493 isParatext "false" @default.
- W4387303493 isRetracted "false" @default.
- W4387303493 workType "article" @default.