Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Spyware Prevention by Classifying End User License Agreements
Responsible organisation
2008 (English)In: New Challenges in Applied Intelligence Technologies / [ed] Nguyen, Ngoc Thanh; Katarzyniak, Radoslaw, Berlin / Heidelberg: Springer , 2008, 373-382 p.Chapter in book (Refereed)Alternative title
Prevention av spionprogram genom klassificering av slutanvändarlicenser (Swedish)
Abstract [en]

We investigate the hypothesis that it is possible to detect from the End User License Agreement (EULA) if the associated software hosts spyware. We apply 15 learning algorithms on a data set consisting of 100 applications with classified EULAs. The results show that 13 algorithms are significantly more accurate than random guessing. Thus,we conclude that the hypothesis can be accepted. Based on the results, we present a novel tool that can be used to prevent spyware by automatically halting application installers and classifying the EULA, giving users the opportunity to make an informed choice about whether to continue with the installation. We discuss positive and negative aspects of this prevention approach and suggest a method for evaluating candidate algorithms for a future implementation.

Abstract [sv]

Vi undersöker hypotesen att det är möjligt att via slutanvändarlicensen detektera om en mjukvaruapplikation innehåller spionprogram eller ej. Vi applicerar 15 inlärningsalgoritmer på en datamängd som innehåller 100 klassificerade slutanvändarlicenser. Resultaten visar att 13 algoritmer är signifikant mer korrekta än slumpvis gissning. Vi drar därför slutsatsen att hypotesen skall accepteras. Baserat på dessa resultat presenterar vi ett nytt verktyg som kan användas för att förhindra installationen av spionprogram genom att automatiskt pausa mjukvaruinstallationer och klassificera slutanvändarlicensen för att ge användaren chansen att göra ett upplyst val om att avbryta eller fortsätta installation. Vi diskuterar positiva och negativa aspekter med denna preventionsansats och föreslår en metod för att utvärdera kandidatalgoritmer för en framtida implementation.

Place, publisher, year, edition, pages
Berlin / Heidelberg: Springer , 2008. 373-382 p.
Keyword [en]
spyware, prevention, classification, machine learning, data mining, neural networks, support vector machines, eula, end user license agreement, application, malware, naive bayes, learning, classifier, candidate
National Category
Computer Science
Identifiers
URN: urn:nbn:se:bth-8563DOI: 10.1007/978-3-540-79355-7_36Local ID: oai:bth.se:forskinfoDBA2596816E1CFE2C125747A00246EEDISBN: 978-3-540-79354-0 (print)OAI: oai:DiVA.org:bth-8563DiVA: diva2:836291
Available from: 2012-09-18 Created: 2008-07-02 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(118 kB)59 downloads
File information
File name FULLTEXT01.pdfFile size 118 kBChecksum SHA-512
b3d25920e24284d6c8649215362cb3f484395e73b773086df2e3ebf21cbd7c0c8e290401b5c3aee6c9e02843142ce245ada91ca113b32c9322e2f514d93d807c
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Lavesson, NiklasBoldt, Martin
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 59 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 38 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf