Risk analysis on Android is aimed at providing metrics to users for evaluating the trustworthiness of the apps they are going to install. Most of current proposals calculate a risk value according to the permissions required by the app through probabilistic functions that often provide unreliable risk values. To overcome such limitations, this paper presents RiskInDroid, a tool for risk analysis of Android apps based on machine learning techniques. Extensive empirical assessments carried out on more than 112K apps and 6K malware samples indicate that RiskInDroid outperforms probabilistic methods in terms of precision and reliability.

Riskindroid: Machine Learning-Based risk analysis on Android

Merlo, Alessio;
2017

Abstract

Risk analysis on Android is aimed at providing metrics to users for evaluating the trustworthiness of the apps they are going to install. Most of current proposals calculate a risk value according to the permissions required by the app through probabilistic functions that often provide unreliable risk values. To overcome such limitations, this paper presents RiskInDroid, a tool for risk analysis of Android apps based on machine learning techniques. Extensive empirical assessments carried out on more than 112K apps and 6K malware samples indicate that RiskInDroid outperforms probabilistic methods in terms of precision and reliability.
File in questo prodotto:
File Dimensione Formato  
ifip-sec-2017.pdf

accesso aperto

Descrizione: Articolo Principale
Tipologia: Documento in Post-print
Dimensione 519.95 kB
Formato Adobe PDF
519.95 kB Adobe PDF Visualizza/Apri

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/11567/886040
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 13
social impact