182K - views

Latent Semantic Analysis and Keyword Extraction for Phishing Classication Gast on LHuillier Alejandro Hevia Department of Computer Science University of Chile Blanco Encalada Santiago Chile Email glh

uchilecl Richard Weber Sebasti an R 305os Department of Industrial Engineering University of Chile Rep ublica 701 Santiago Chile Email rwebersrios diiuchilecl Abstract Phishing email fraud has been considered as one of the main cyberthreats over the

Embed :
Pdf Download Link

Download Pdf - The PPT/PDF document "Latent Semantic Analysis and Keyword Ext..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Latent Semantic Analysis and Keyword Extraction for Phishing Classication Gast on LHuillier Alejandro Hevia Department of Computer Science University of Chile Blanco Encalada Santiago Chile Email glh






Presentation on theme: "Latent Semantic Analysis and Keyword Extraction for Phishing Classication Gast on LHuillier Alejandro Hevia Department of Computer Science University of Chile Blanco Encalada Santiago Chile Email glh"ā€” Presentation transcript:

ORKNowadays,inthecyber-crime keepraisingastheinternetpenetrationinoureverydaylifeincreases.DifferenttextminingtechniquesforphishingŽlteringhavebeenproposed.In[1],LogisticRegression,SupportVectorMachines(SVMs),andRandomForestsareusedtoestimateclassiŽersforthecorrectlabelingofemailmessages.Byusingofmoresophisticatedtextminingtechniques,Bergholzetal.([3],[4])proposedanovelcharacterizationofemailsusingaClass-Topicmodel.Forphishingfeatureextractionseveralmethodologieshavebeendeveloped[1],[2],[4],[7],while combinationofstructuralbasicfeatures$,whichareinde-pendentfromtheothercontentbasedfeaturesset#,!and".However,thesesetsarenotindependentfromeachother.Theyarerepresentedbybinaryfeatures,indicatingwhetherakeywordortopicispresentedinagivenmessage,whoseintersectiondescribesaŽnalsetoffeaturesthatrepresentsa tiveclassiŽermodelsrepresentedbylogisticregression.ThissupportstheussualpreferenceofSVMsforclassiŽcationtasks,speciallyintext-miningapplications. GerhardPaass,andSiehyunStrobel.NewŽlteringapproachesforphishingemail.