Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386101170> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4386101170 endingPage "110931" @default.
- W4386101170 startingPage "110931" @default.
- W4386101170 abstract "Attackers attempt to bias the outputs of collaborative recommender systems by maliciously rating goods or services. To detect such attacks, many deep learning-based detection methods have been proposed and shown to be feasible. However, most methods require a large number of labeled user profiles for training to ensure good detection performance. To address this issue, in this paper, we propose a deep semisupervised detection approach based on the improved Meta Pseudo Labels, named DSSD-ImMPL. DSSD-ImMPL can achieve high detection performance given a small number of labeled training samples and a certain number of unlabeled training samples. We first improve the Meta Pseudo Labels method by generating a group of student networks by an experienced teacher network instead of only one student network in the original Meta Pseudo Labels method to improve the classification performance. Then, we use the group of student networks to detect the recommendation attack. The detection performance is verified with classical, mixed, GSA-GANs, and real attacks on three benchmark datasets by comparing DSSD-ImMPL with the state-of-the-art detection methods." @default.
- W4386101170 created "2023-08-24" @default.
- W4386101170 creator A5033996313 @default.
- W4386101170 creator A5066196976 @default.
- W4386101170 creator A5070345022 @default.
- W4386101170 date "2023-11-01" @default.
- W4386101170 modified "2023-09-26" @default.
- W4386101170 title "Recommendation attack detection based on improved Meta Pseudo Labels" @default.
- W4386101170 cites W1969347587 @default.
- W4386101170 cites W2000855935 @default.
- W4386101170 cites W2070107618 @default.
- W4386101170 cites W2122114437 @default.
- W4386101170 cites W2158698691 @default.
- W4386101170 cites W2413004790 @default.
- W4386101170 cites W2791170775 @default.
- W4386101170 cites W2794121917 @default.
- W4386101170 cites W2801227775 @default.
- W4386101170 cites W2890884621 @default.
- W4386101170 cites W2979327990 @default.
- W4386101170 cites W3075585526 @default.
- W4386101170 cites W3097342189 @default.
- W4386101170 cites W3179806144 @default.
- W4386101170 cites W4200542463 @default.
- W4386101170 cites W4220897279 @default.
- W4386101170 cites W4315488047 @default.
- W4386101170 cites W4362451421 @default.
- W4386101170 doi "https://doi.org/10.1016/j.knosys.2023.110931" @default.
- W4386101170 hasPublicationYear "2023" @default.
- W4386101170 type Work @default.
- W4386101170 citedByCount "0" @default.
- W4386101170 crossrefType "journal-article" @default.
- W4386101170 hasAuthorship W4386101170A5033996313 @default.
- W4386101170 hasAuthorship W4386101170A5066196976 @default.
- W4386101170 hasAuthorship W4386101170A5070345022 @default.
- W4386101170 hasConcept C108583219 @default.
- W4386101170 hasConcept C119857082 @default.
- W4386101170 hasConcept C124101348 @default.
- W4386101170 hasConcept C13280743 @default.
- W4386101170 hasConcept C153180895 @default.
- W4386101170 hasConcept C154945302 @default.
- W4386101170 hasConcept C162324750 @default.
- W4386101170 hasConcept C185798385 @default.
- W4386101170 hasConcept C187736073 @default.
- W4386101170 hasConcept C205649164 @default.
- W4386101170 hasConcept C2780451532 @default.
- W4386101170 hasConcept C2781002164 @default.
- W4386101170 hasConcept C41008148 @default.
- W4386101170 hasConcept C557471498 @default.
- W4386101170 hasConceptScore W4386101170C108583219 @default.
- W4386101170 hasConceptScore W4386101170C119857082 @default.
- W4386101170 hasConceptScore W4386101170C124101348 @default.
- W4386101170 hasConceptScore W4386101170C13280743 @default.
- W4386101170 hasConceptScore W4386101170C153180895 @default.
- W4386101170 hasConceptScore W4386101170C154945302 @default.
- W4386101170 hasConceptScore W4386101170C162324750 @default.
- W4386101170 hasConceptScore W4386101170C185798385 @default.
- W4386101170 hasConceptScore W4386101170C187736073 @default.
- W4386101170 hasConceptScore W4386101170C205649164 @default.
- W4386101170 hasConceptScore W4386101170C2780451532 @default.
- W4386101170 hasConceptScore W4386101170C2781002164 @default.
- W4386101170 hasConceptScore W4386101170C41008148 @default.
- W4386101170 hasConceptScore W4386101170C557471498 @default.
- W4386101170 hasFunder F4320324174 @default.
- W4386101170 hasLocation W43861011701 @default.
- W4386101170 hasOpenAccess W4386101170 @default.
- W4386101170 hasPrimaryLocation W43861011701 @default.
- W4386101170 hasRelatedWork W2795261237 @default.
- W4386101170 hasRelatedWork W3014300295 @default.
- W4386101170 hasRelatedWork W3164822677 @default.
- W4386101170 hasRelatedWork W4223943233 @default.
- W4386101170 hasRelatedWork W4225161397 @default.
- W4386101170 hasRelatedWork W4312200629 @default.
- W4386101170 hasRelatedWork W4360585206 @default.
- W4386101170 hasRelatedWork W4364306694 @default.
- W4386101170 hasRelatedWork W4380075502 @default.
- W4386101170 hasRelatedWork W4380086463 @default.
- W4386101170 hasVolume "279" @default.
- W4386101170 isParatext "false" @default.
- W4386101170 isRetracted "false" @default.
- W4386101170 workType "article" @default.