prikaz prve stranice dokumenta Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja
Access restricted to authenticated users
master's thesis
Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja
2021. urn:nbn:hr:179:344404
Novak, Nikola
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Novak, N. (2021). Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:344404

Novak, Nikola. "Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:344404

Novak, Nikola. "Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:344404

Novak, N. (2021). 'Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 15 November 2024, https://urn.nsk.hr/urn:nbn:hr:179:344404

Novak N. Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 November 15] Available at: https://urn.nsk.hr/urn:nbn:hr:179:344404

N. Novak, "Detekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:344404

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija zlonamjernog softvera na Android operacijskom sustavu primjenom dubinskog učenja
Title (english)Malware detection on the Android operating system using deep learning
AuthorNikola Novak
MentorAna Kuzmanić Skelin (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-07-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu dan je kratki pregled arhitekture Android sustava, njegovog sigurnosnog modela, te sigurnosti Android aplikacija. Najveći propust kod sigurnosti su sami korisnici, jer zlonamjerni softver ne može sam od sebe završiti na korisnikovom uređaju, kamoli dobiti sve potrebne dozvole kako bi mogao napraviti štetu. Napravljen je i pregled zlonamjernih android aplikacija, koje ne pokazuju znakove usporavanja u zadnjih par godina, pogotovo za vrijeme aktualne pandemije. Također su opisane trenutno popularne vrste i kampanje zlonamjernih aplikacija na Androidu. Dan je kratki uvod u metode strojnog učenja koje bi se mogle koristiti za detekciju zlonamjernog softvera na Androidu, te detaljni pregled dubinskog učenja i neuronskih mreža. Predstavljen je cjeloviti proces otkrivanja zlonamjernih Android aplikacija na temelju dubinskog učenja koji se sastoji od prikupljanja uzoraka, predobrade podataka, odabira značajki, treniranja modela, optimizacije modela, evaluacije modela, te konačno korištenja modela za predviđanje i rješavanje praktičnih problema. Cjelokupni proces demonstriran je na CICMalDroid 2020 skupu podataka.
Abstract (english)
This master’s thesis deals with the topic Android malware detection using deep learning. First, a brief overview of the architecture of the Android system, its security model, and the security of Android applications is given. The biggest security flaw are the users themselves, because the malware cannot end up on the user’s device on its own, nor get all the necessary permissions to do damage. Next, a review of malicious Android applications has also been made, where the currently popular types and campaigns of malicious applications on Android are described. A brief introduction to machine learning methods that could be used to detect malware on Android is given, as well as a detailed overview of deep learning and neural networks. A comprehensive process of detecting malicious Android applications based on deep learning is presented, consisting of sample collection, data pre-processing, feature selection, model training, model optimization, model evaluation, and using the model to predict and solve practical problems. The process is demonstrated on the CICMalDroid 2020 dataset.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:344404
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2021-11-26 11:54:44