Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319079580> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4319079580 endingPage "728" @default.
- W4319079580 startingPage "710" @default.
- W4319079580 abstract "As social networks become indispensable for people’s daily lives, inference attacks pose significant threat to users’ privacy where attackers can infiltrate users’ information and infer their private attributes. In particular, social networks are represented as graph-structured data, maintaining rich user activities and complex relationships among them. This enables attackers to deploy state-of-the-art graph neural networks (GNNs) to automate attribute inference attacks for users’ privacy disclosure. To address this challenge, in this paper, we leverage the vulnerability of GNNs to adversarial attacks, and propose a new graph adversarial method, called Attribute-Obfuscating Attack (AttrOBF) to mislead GNNs into misclassification and thus protect user attribute privacy against GNN-based inference attacks on social networks. Different from the prior attacks using perturbations on graph structure or node features, AttrOBF provides a more practical formulation by obfuscating optimal training user attribute values, and also advances the attribute obfuscation by solving the unavailability issue of test attribute annotations, black-box setting, bi-level optimization, and non-differentiable obfuscating operation. We demonstrate the effectiveness of AttrOBF on user attribute obfuscation by extensive experiments over three real-world social network datasets. We believe our work yields great potential of applying adversarial attacks to attribute protection on social networks." @default.
- W4319079580 created "2023-02-04" @default.
- W4319079580 creator A5008435786 @default.
- W4319079580 creator A5010903174 @default.
- W4319079580 creator A5017524689 @default.
- W4319079580 date "2023-01-01" @default.
- W4319079580 modified "2023-09-29" @default.
- W4319079580 title "Adversary for Social Good: Leveraging Attribute-Obfuscating Attack to Protect User Privacy on Social Networks" @default.
- W4319079580 cites W2152284345 @default.
- W4319079580 cites W2604776663 @default.
- W4319079580 cites W2605289356 @default.
- W4319079580 cites W2751888965 @default.
- W4319079580 cites W2780061022 @default.
- W4319079580 cites W2781896769 @default.
- W4319079580 cites W2803831897 @default.
- W4319079580 cites W2962857818 @default.
- W4319079580 cites W2963843518 @default.
- W4319079580 cites W2964211797 @default.
- W4319079580 cites W2964583308 @default.
- W4319079580 cites W2964965220 @default.
- W4319079580 cites W2964971928 @default.
- W4319079580 cites W2965477817 @default.
- W4319079580 cites W2966149470 @default.
- W4319079580 cites W2997645877 @default.
- W4319079580 cites W3035096461 @default.
- W4319079580 cites W3095461782 @default.
- W4319079580 cites W3100848837 @default.
- W4319079580 cites W3127927415 @default.
- W4319079580 cites W3129990286 @default.
- W4319079580 cites W3130640456 @default.
- W4319079580 cites W3198200562 @default.
- W4319079580 doi "https://doi.org/10.1007/978-3-031-25538-0_37" @default.
- W4319079580 hasPublicationYear "2023" @default.
- W4319079580 type Work @default.
- W4319079580 citedByCount "0" @default.
- W4319079580 crossrefType "book-chapter" @default.
- W4319079580 hasAuthorship W4319079580A5008435786 @default.
- W4319079580 hasAuthorship W4319079580A5010903174 @default.
- W4319079580 hasAuthorship W4319079580A5017524689 @default.
- W4319079580 hasConcept C108827166 @default.
- W4319079580 hasConcept C132525143 @default.
- W4319079580 hasConcept C136764020 @default.
- W4319079580 hasConcept C153083717 @default.
- W4319079580 hasConcept C154945302 @default.
- W4319079580 hasConcept C2776214188 @default.
- W4319079580 hasConcept C2777522414 @default.
- W4319079580 hasConcept C37736160 @default.
- W4319079580 hasConcept C38652104 @default.
- W4319079580 hasConcept C40305131 @default.
- W4319079580 hasConcept C41008148 @default.
- W4319079580 hasConcept C41065033 @default.
- W4319079580 hasConcept C4727928 @default.
- W4319079580 hasConcept C518677369 @default.
- W4319079580 hasConcept C80444323 @default.
- W4319079580 hasConceptScore W4319079580C108827166 @default.
- W4319079580 hasConceptScore W4319079580C132525143 @default.
- W4319079580 hasConceptScore W4319079580C136764020 @default.
- W4319079580 hasConceptScore W4319079580C153083717 @default.
- W4319079580 hasConceptScore W4319079580C154945302 @default.
- W4319079580 hasConceptScore W4319079580C2776214188 @default.
- W4319079580 hasConceptScore W4319079580C2777522414 @default.
- W4319079580 hasConceptScore W4319079580C37736160 @default.
- W4319079580 hasConceptScore W4319079580C38652104 @default.
- W4319079580 hasConceptScore W4319079580C40305131 @default.
- W4319079580 hasConceptScore W4319079580C41008148 @default.
- W4319079580 hasConceptScore W4319079580C41065033 @default.
- W4319079580 hasConceptScore W4319079580C4727928 @default.
- W4319079580 hasConceptScore W4319079580C518677369 @default.
- W4319079580 hasConceptScore W4319079580C80444323 @default.
- W4319079580 hasLocation W43190795801 @default.
- W4319079580 hasOpenAccess W4319079580 @default.
- W4319079580 hasPrimaryLocation W43190795801 @default.
- W4319079580 hasRelatedWork W1583236736 @default.
- W4319079580 hasRelatedWork W2522301850 @default.
- W4319079580 hasRelatedWork W2891261571 @default.
- W4319079580 hasRelatedWork W3012515814 @default.
- W4319079580 hasRelatedWork W3090107331 @default.
- W4319079580 hasRelatedWork W3133898321 @default.
- W4319079580 hasRelatedWork W4235659105 @default.
- W4319079580 hasRelatedWork W4286307889 @default.
- W4319079580 hasRelatedWork W4307930337 @default.
- W4319079580 hasRelatedWork W4362599004 @default.
- W4319079580 isParatext "false" @default.
- W4319079580 isRetracted "false" @default.
- W4319079580 workType "book-chapter" @default.