RiskInDroid: Machine Learning-Based Risk Analysis on Android

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.
Type de document :
Communication dans un congrès
Sabrina De Capitani di Vimercati; Fabio Martinelli. 32th IFIP International Conference on ICT Systems Security and Privacy Protection (SEC), May 2017, Rome, Italy. Springer International Publishing, IFIP Advances in Information and Communication Technology, AICT-502, pp.538-552, 2017, ICT Systems Security and Privacy Protection. 〈10.1007/978-3-319-58469-0_36〉
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01648990
Contributeur : Hal Ifip <>
Soumis le : lundi 27 novembre 2017 - 10:31:02
Dernière modification le : lundi 27 novembre 2017 - 10:34:20

Fichier

 Accès restreint
Fichier visible le : 2020-01-01

Connectez-vous pour demander l'accès au fichier

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Alessio Merlo, Gabriel Georgiu. RiskInDroid: Machine Learning-Based Risk Analysis on Android. Sabrina De Capitani di Vimercati; Fabio Martinelli. 32th IFIP International Conference on ICT Systems Security and Privacy Protection (SEC), May 2017, Rome, Italy. Springer International Publishing, IFIP Advances in Information and Communication Technology, AICT-502, pp.538-552, 2017, ICT Systems Security and Privacy Protection. 〈10.1007/978-3-319-58469-0_36〉. 〈hal-01648990〉

Partager

Métriques

Consultations de la notice

120