File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Unsupervised euclidean distance attack on network embedding

TitleUnsupervised euclidean distance attack on network embedding
Authors
KeywordsAdversarial attack
Euclidean distance
Network algorithm
Network embedding
Unsupervised learning
Issue Date2020
Citation
Proceedings - 2020 IEEE 5th International Conference on Data Science in Cyberspace, DSC 2020, 2020, p. 71-77 How to Cite?
AbstractConsidering the wide application of network embedding methods in graph data mining, inspired by adversarial attacks in deep learning, a genetic algorithm-based Euclidean distance attack strategy is proposed to attack the network embedding method, thereby preventing structure information being discovered. EDA focuses on disturbing the Euclidean distance between a pair of nodes in the embedding space as much as possible through minimal modifications of the network structure. Since many downstream network algorithms, such as community detection and node classification, rely on the Euclidean distance between nodes to evaluate their similarity in the embedded space, EDA can be regarded as a general attack on various network algorithms. Different from traditional supervised attack strategies, EDA does not need labeling information, it is an unsupervised network embedding attack method. Experiments on a set of real networks demonstrate that the proposed EDA method can significantly reduce the performance of DeepWalk-based networking algorithms, i.e., community detection and node classification, and its performance is superior to several heuristic attack strategies.
Persistent Identifierhttp://hdl.handle.net/10722/330667

 

DC FieldValueLanguage
dc.contributor.authorYu, Shanqing-
dc.contributor.authorZheng, Jun-
dc.contributor.authorChen, Jinyin-
dc.contributor.authorXuan, Qi-
dc.contributor.authorZhang, Qingpeng-
dc.date.accessioned2023-09-05T12:12:57Z-
dc.date.available2023-09-05T12:12:57Z-
dc.date.issued2020-
dc.identifier.citationProceedings - 2020 IEEE 5th International Conference on Data Science in Cyberspace, DSC 2020, 2020, p. 71-77-
dc.identifier.urihttp://hdl.handle.net/10722/330667-
dc.description.abstractConsidering the wide application of network embedding methods in graph data mining, inspired by adversarial attacks in deep learning, a genetic algorithm-based Euclidean distance attack strategy is proposed to attack the network embedding method, thereby preventing structure information being discovered. EDA focuses on disturbing the Euclidean distance between a pair of nodes in the embedding space as much as possible through minimal modifications of the network structure. Since many downstream network algorithms, such as community detection and node classification, rely on the Euclidean distance between nodes to evaluate their similarity in the embedded space, EDA can be regarded as a general attack on various network algorithms. Different from traditional supervised attack strategies, EDA does not need labeling information, it is an unsupervised network embedding attack method. Experiments on a set of real networks demonstrate that the proposed EDA method can significantly reduce the performance of DeepWalk-based networking algorithms, i.e., community detection and node classification, and its performance is superior to several heuristic attack strategies.-
dc.languageeng-
dc.relation.ispartofProceedings - 2020 IEEE 5th International Conference on Data Science in Cyberspace, DSC 2020-
dc.subjectAdversarial attack-
dc.subjectEuclidean distance-
dc.subjectNetwork algorithm-
dc.subjectNetwork embedding-
dc.subjectUnsupervised learning-
dc.titleUnsupervised euclidean distance attack on network embedding-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/DSC50466.2020.00019-
dc.identifier.scopuseid_2-s2.0-85092057733-
dc.identifier.spage71-
dc.identifier.epage77-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats