RiskInDroid: Machine Learning-Based Risk Analysis on Android - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

RiskInDroid: Machine Learning-Based Risk Analysis on Android

(1) , (2)
1
2
Gabriel Claudiu Georgiu
  • Function : Author
  • PersonId : 1023778

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 112 K apps and 6 K malware samples indicate that RiskInDroid outperforms probabilistic methods in terms of precision and reliability.
Fichier principal
Vignette du fichier
449885_1_En_36_Chapter.pdf (520.63 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01648990 , version 1 (27-11-2017)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Alessio Merlo, Gabriel Claudiu Georgiu. RiskInDroid: Machine Learning-Based Risk Analysis on Android. 32th IFIP International Conference on ICT Systems Security and Privacy Protection (SEC), May 2017, Rome, Italy. pp.538-552, ⟨10.1007/978-3-319-58469-0_36⟩. ⟨hal-01648990⟩
377 View
124 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More