The huge diffusion of the so-called smartphone devices is boosting the malware writer community to write more and more aggressive software targeting the mobile platforms. While scientific community has largely studied malware on Android platform, few attention is paid to iOS applications, probably to their closed-source nature. In this paper, in order to fill this gap, we propose a method to identify malicious application on Apple environment. Our method relies on a feature vector extracted by static analysis. Experiments, performed with 20 different machine learning algorithms, demonstrate that malware iOS applications are discriminated by trusted ones with a precision equal to 0.971 and a recall equal to 1.

Machine learning meets ios malware: Identifying malicious applications on apple environment

Mercaldo F.
2017-01-01

Abstract

The huge diffusion of the so-called smartphone devices is boosting the malware writer community to write more and more aggressive software targeting the mobile platforms. While scientific community has largely studied malware on Android platform, few attention is paid to iOS applications, probably to their closed-source nature. In this paper, in order to fill this gap, we propose a method to identify malicious application on Apple environment. Our method relies on a feature vector extracted by static analysis. Experiments, performed with 20 different machine learning algorithms, demonstrate that malware iOS applications are discriminated by trusted ones with a precision equal to 0.971 and a recall equal to 1.
2017
978-989-758-209-7
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11695/115425
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 30
  • ???jsp.display-item.citation.isi??? ND
social impact