The increasing diffusion of smart devices, along with the dynamism of the mobile applications ecosystem, are boosting the production of malware for the Android platform. So far, many different methods have been developed for detecting Android malware, based on either static or dynamic analysis. The main limitations of existing methods include: low accuracy, proneness to evasion techniques, and weak validation, often limited to emulators or modified kernels. We propose an Android malware detection method, based on sequences of system calls, that overcomes these limitations. The assumption is that malicious behaviors (e.g., sending high premium rate SMS, cyphering data for ransom, botnet capabilities, and so on) are implemented by specific system calls sequences: yet, no apriori knowledge is available about which sequences are associated with which malicious behaviors, in particular in the mobile applications ecosystem where new malware and non-malware applications continuously arise. Hence, we use Machine Learning to automatically learn these associations (a sort of "fingerprint" of the malware); then we exploit them to actually detect malware. Experimentation on 20000 execution traces of 2000 applications (1000 of them being malware belonging to different malware families), performed on a real device, shows promising results: we obtain a detection accuracy of 97%. Moreover, we show that the proposed method can cope with the dynamism of the mobile apps ecosystem, since it can detect unknown malware.

Detecting Android malware using sequences of system calls

MEDVET, Eric;
2015

Abstract

The increasing diffusion of smart devices, along with the dynamism of the mobile applications ecosystem, are boosting the production of malware for the Android platform. So far, many different methods have been developed for detecting Android malware, based on either static or dynamic analysis. The main limitations of existing methods include: low accuracy, proneness to evasion techniques, and weak validation, often limited to emulators or modified kernels. We propose an Android malware detection method, based on sequences of system calls, that overcomes these limitations. The assumption is that malicious behaviors (e.g., sending high premium rate SMS, cyphering data for ransom, botnet capabilities, and so on) are implemented by specific system calls sequences: yet, no apriori knowledge is available about which sequences are associated with which malicious behaviors, in particular in the mobile applications ecosystem where new malware and non-malware applications continuously arise. Hence, we use Machine Learning to automatically learn these associations (a sort of "fingerprint" of the malware); then we exploit them to actually detect malware. Experimentation on 20000 execution traces of 2000 applications (1000 of them being malware belonging to different malware families), performed on a real device, shows promising results: we obtain a detection accuracy of 97%. Moreover, we show that the proposed method can cope with the dynamism of the mobile apps ecosystem, since it can detect unknown malware.
File in questo prodotto:
File Dimensione Formato  
2015_DeMobile_DetectionMalwareAndroidSyscalls (5).pdf

non disponibili

Descrizione: Articolo principale
Tipologia: Bozza finale post-referaggio (post-print)
Licenza: Digital Rights Management non definito
Dimensione 215.17 kB
Formato Adobe PDF
215.17 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
p13-canfora.pdf

non disponibili

Descrizione: Articolo principale
Tipologia: Documento in Versione Editoriale
Licenza: Digital Rights Management non definito
Dimensione 263.92 kB
Formato Adobe PDF
263.92 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: http://hdl.handle.net/11368/2864920
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 92
  • ???jsp.display-item.citation.isi??? ND
social impact