FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313305480> ?p ?o ?g. }

• W4313305480 abstract "Graph Neural Networks (GNNs) have been widely applied to different tasks such as bioinformatics, drug design, and social networks. However, recent studies have shown that GNNs are vulnerable to adversarial attacks which aim to mislead the node or subgraph classification prediction by adding subtle perturbations. Detecting these attacks is challenging due to the small magnitude of perturbation and the discrete nature of graph data. In this paper, we propose a general adversarial edge detection pipeline EDoG without requiring knowledge of the attack strategies based on graph generation. Specifically, we propose a novel graph generation approach combined with link prediction to detect suspicious adversarial edges. To effectively train the graph generative model, we sample several sub-graphs from the given graph data. We show that since the number of adversarial edges is usually low in practice, with low probability the sampled sub-graphs will contain adversarial edges based on the union bound. In addition, considering the strong attacks which perturb a large number of edges, we propose a set of novel features to perform outlier detection as the preprocessing for our detection. Extensive experimental results on three real-world graph datasets including a private transaction rule dataset from a major company and two types of synthetic graphs with controlled properties show that EDoG can achieve above 0.8 AUC against four state-of-the-art unseen attack strategies without requiring any knowledge about the attack type; and around 0.85 with knowledge of the attack type. EDoG significantly outperforms traditional malicious edge detection baselines. We also show that an adaptive attack with full knowledge of our detection pipeline is difficult to bypass it." @default.
• W4313305480 created "2023-01-06" @default.
• W4313305480 creator A5010398748 @default.
• W4313305480 creator A5028693742 @default.
• W4313305480 creator A5031954035 @default.
• W4313305480 creator A5034995105 @default.
• W4313305480 creator A5040046281 @default.
• W4313305480 creator A5049816813 @default.
• W4313305480 date "2022-12-27" @default.
• W4313305480 modified "2023-09-23" @default.
• W4313305480 title "EDoG: Adversarial Edge Detection For Graph Neural Networks" @default.
• W4313305480 doi "https://doi.org/10.48550/arxiv.2212.13607" @default.
• W4313305480 hasPublicationYear "2022" @default.
• W4313305480 type Work @default.
• W4313305480 citedByCount "0" @default.
• W4313305480 crossrefType "posted-content" @default.
• W4313305480 hasAuthorship W4313305480A5010398748 @default.
• W4313305480 hasAuthorship W4313305480A5028693742 @default.
• W4313305480 hasAuthorship W4313305480A5031954035 @default.
• W4313305480 hasAuthorship W4313305480A5034995105 @default.
• W4313305480 hasAuthorship W4313305480A5040046281 @default.
• W4313305480 hasAuthorship W4313305480A5049816813 @default.
• W4313305480 hasBestOaLocation W43133054801 @default.
• W4313305480 hasConcept C119857082 @default.
• W4313305480 hasConcept C124101348 @default.
• W4313305480 hasConcept C132525143 @default.
• W4313305480 hasConcept C153180895 @default.
• W4313305480 hasConcept C154945302 @default.
• W4313305480 hasConcept C34736171 @default.
• W4313305480 hasConcept C37736160 @default.
• W4313305480 hasConcept C41008148 @default.
• W4313305480 hasConcept C80444323 @default.
• W4313305480 hasConceptScore W4313305480C119857082 @default.
• W4313305480 hasConceptScore W4313305480C124101348 @default.
• W4313305480 hasConceptScore W4313305480C132525143 @default.
• W4313305480 hasConceptScore W4313305480C153180895 @default.
• W4313305480 hasConceptScore W4313305480C154945302 @default.
• W4313305480 hasConceptScore W4313305480C34736171 @default.
• W4313305480 hasConceptScore W4313305480C37736160 @default.
• W4313305480 hasConceptScore W4313305480C41008148 @default.
• W4313305480 hasConceptScore W4313305480C80444323 @default.
• W4313305480 hasLocation W43133054801 @default.
• W4313305480 hasOpenAccess W4313305480 @default.
• W4313305480 hasPrimaryLocation W43133054801 @default.
• W4313305480 hasRelatedWork W1502614025 @default.
• W4313305480 hasRelatedWork W2066259560 @default.
• W4313305480 hasRelatedWork W2126100045 @default.
• W4313305480 hasRelatedWork W2262783296 @default.
• W4313305480 hasRelatedWork W2380927352 @default.
• W4313305480 hasRelatedWork W2391959412 @default.
• W4313305480 hasRelatedWork W2728578317 @default.
• W4313305480 hasRelatedWork W3003836766 @default.
• W4313305480 hasRelatedWork W3129710645 @default.
• W4313305480 hasRelatedWork W4211209597 @default.
• W4313305480 isParatext "false" @default.
• W4313305480 isRetracted "false" @default.
• W4313305480 workType "article" @default.