A Privacy-Preserving Word Embedding Text Classification Model Based on Privacy Boundary Constructed by Deep Belief Network

aut.relation.journalMultimedia Tools and Applications
dc.contributor.authorMa, Bo
dc.contributor.authorLai, Edmund
dc.contributor.authorYan, Wei Qi
dc.contributor.authorWu, Jinsong
dc.date.accessioned2023-09-17T21:56:30Z
dc.date.available2023-09-17T21:56:30Z
dc.date.issued2023-09-15
dc.description.abstractTo effectively extract and classify the information from reports or documents and protect the privacy of the extracted results, we propose a privacy classification named Word Embedding Combination Privacy-preserving Support Vector Machine (WECPPSVM) model to classify the text. In addition, this paper also proposes the Privacy-preserving Distribution and Independent Frequent Subsequence Extraction Algorithm (PPDIFSEA), which calculates the degree of independence of the training data input to the classification model by training the Deep Belief Network(DBN) in PPDIFSEA, then obtains the Privacy Boundary(PB). PB is an indispensable condition for both data sampling and privacy noise generation. And this model can protect privacy by injecting the privacy noise into the classification result, this method can interfere with the background knowledge-based privacy attack. Our quantitative analysis shows that the WECPPSVM proposed in this paper can approach mainstream text classification algorithms in terms of text classification accuracy while preserving privacy without increasing computational complexity. In addition, the fusion study and privacy threat evaluation also verify that the proposed PPDIFSEA method combined with WECPPSVM achieves an acceptable level of classification accuracy and privacy protection.
dc.identifier.citationMultimedia Tools and Applications, ISSN: 1380-7501 (Print); 1573-7721 (Online), Springer Science and Business Media LLC. doi: 10.1007/s11042-023-15623-3
dc.identifier.doi10.1007/s11042-023-15623-3
dc.identifier.issn1380-7501
dc.identifier.issn1573-7721
dc.identifier.urihttp://hdl.handle.net/10292/16693
dc.languageen
dc.publisherSpringer Science and Business Media LLC
dc.relation.urihttps://link.springer.com/article/10.1007/s11042-023-15623-3
dc.rights.accessrightsOpenAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject0801 Artificial Intelligence and Image Processing
dc.subject0803 Computer Software
dc.subject0805 Distributed Computing
dc.subject0806 Information Systems
dc.subjectArtificial Intelligence & Image Processing
dc.subjectSoftware Engineering
dc.subject4009 Electronics, sensors and digital hardware
dc.subject4603 Computer vision and multimedia computation
dc.subject4605 Data management and data science
dc.subject4606 Distributed computing and systems software
dc.titleA Privacy-Preserving Word Embedding Text Classification Model Based on Privacy Boundary Constructed by Deep Belief Network
dc.typeJournal Article
pubs.elements-id523510
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Ma_Bo_s11042-023-15623-3.pdf
Size:
3.08 MB
Format:
Adobe Portable Document Format
Description:
Journal article
Loading...
Thumbnail Image
Name:
s11042-023-15623-3.pdf
Size:
3.08 MB
Format:
Adobe Portable Document Format
Description: