Show simple item record

dc.contributor.authorPhan, Tien Jr
dc.date.accessioned2018-04-19T10:35:41Z
dc.date.available2018-04-19T10:35:41Z
dc.date.issued2018-04-19T10:35:41Z
dc.identifier.urihttp://hdl.handle.net/10222/73875
dc.description.abstractIdentifying compromised accounts on online social networks that are used for phishing attacks or sending spam messages is still one of the most challenging problems of cyber security. In this research, the author explore an artificial neural network based language model to differentiate the writing styles of different users on short text messages. In doing so, the aim is to be able to identify compromised user accounts. The results obtained indicate that one can learn the language model on one dataset and can generalize it to different datasets with high accuracy and low false alarm rates without any modifications to the language model.en_US
dc.language.isoenen_US
dc.subjectCompromised usersen_US
dc.subjectForensics analysisen_US
dc.subjectLanguage modelen_US
dc.subjectArtificial neural networksen_US
dc.titleA MACHINE LEARNING BASED LANGUAGE MODEL TO IDENTIFY COMPROMISED USERSen_US
dc.date.defence2018-04-17
dc.contributor.departmentFaculty of Computer Scienceen_US
dc.contributor.degreeMaster of Computer Scienceen_US
dc.contributor.external-examinern/aen_US
dc.contributor.graduate-coordinatorDr. Norbert Zehen_US
dc.contributor.thesis-readerDr. Andrew McIntyreen_US
dc.contributor.thesis-readerDr. Malcolm Heywooden_US
dc.contributor.thesis-supervisorDr. Nur Zincir-Heywooden_US
dc.contributor.ethics-approvalNot Applicableen_US
dc.contributor.manuscriptsNoen_US
dc.contributor.copyright-releaseNoen_US
 Find Full text

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record