Publication:
A new mobile botnet classification based on permission and API calls

Simple item page
dc.Conferencecode132013
dc.Conferencedate6 September 2017 through 8 September 2017
dc.Conferencename7th International Conference on Emerging Security Technologies, EST 2017
dc.FundingDetailsUniversiti Sains Islam Malaysia,�USIM: USIM/FRGS/FST/32/50114 Ministry of Higher Education, Malaysia,�MOHE
dc.FundingDetailsThe authors would like to express their gratitude to Ministry of Higher Education (MOHE), Malaysia and Universiti Sains Islam Malaysia (USIM) for the support and facilities provided. This research paper is supported by MOHE grant: [USIM/FRGS/FST/32/50114].
dc.citedby5
dc.contributor.affiliationsFaculty of Science and Technology
dc.contributor.affiliationsUniversiti Sains Islam Malaysia (USIM)
dc.contributor.authorYusof M.en_US
dc.contributor.authorSaudi M.M.en_US
dc.contributor.authorRidzuan F.en_US
dc.date.accessioned2024-05-28T08:27:38Z
dc.date.available2024-05-28T08:27:38Z
dc.date.issued2017
dc.description.abstractCurrently, mobile botnet attacks have shifted from computers to smartphones due to its functionality, ease to exploit, and based on financial intention. Mostly, it attacks Android due to its popularity and high usage among end users. Every day, more and more malicious mobile applications (apps) with the botnet capability have been developed to exploit end users' smartphones. Therefore, this paper presents a new mobile botnet classification based on permission and Application Programming Interface (API) calls in the smartphone. This classification is developed using static analysis in a controlled lab environment and the Drebin dataset is used as the training dataset. 800 apps from the Google Play Store have been chosen randomly to test the proposed classification. As a result, 16 permissions and 31 API calls that are most related with mobile botnet have been extracted using feature selection and later classified and tested using machine learning algorithms. The experimental result shows that the Random Forest Algorithm has achieved the highest detection accuracy of 99.4% with the lowest false positive rate of 16.1% as compared to other machine learning algorithms. This new classification can be used as the input for mobile botnet detection for future work, especially for financial matters. � 2017 IEEE.
dc.description.natureFinalen_US
dc.identifier.ArtNo8090410
dc.identifier.doi10.1109/EST.2017.8090410
dc.identifier.epage127
dc.identifier.isbn9781540000000
dc.identifier.scopus2-s2.0-85041178082
dc.identifier.spage122
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85041178082&doi=10.1109%2fEST.2017.8090410&partnerID=40&md5=3f24ef3bb85629335c9f226172936645
dc.identifier.urihttps://oarep.usim.edu.my/handle/123456789/8809
dc.languageEnglish
dc.language.isoen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofProceedings - 2017 7th International Conference on Emerging Security Technologies, EST 2017
dc.sourceScopus
dc.subjectandroid botneten_US
dc.subjectmachine learningen_US
dc.subjectmobile botnet classificationen_US
dc.subjectrandom forest algorithmen_US
dc.subjectstatic analysisen_US
dc.subjectAndroid (operating system)en_US
dc.subjectApplication programming interfaces (API)en_US
dc.subjectArtificial intelligenceen_US
dc.subjectBotneten_US
dc.subjectClassification (of information)en_US
dc.subjectDecision treesen_US
dc.subjectLearning systemsen_US
dc.subjectSmartphonesen_US
dc.subjectStatic analysisen_US
dc.subjectBotnet detectionsen_US
dc.subjectDetection accuracyen_US
dc.subjectEnd usersen_US
dc.subjectFalse positive ratesen_US
dc.subjectGoogle playsen_US
dc.subjectMobile applicationsen_US
dc.titleA new mobile botnet classification based on permission and API calls
dc.typeConference Paperen_US
dspace.entity.typePublication

Files

Collections

Scopus