UCL  IRIS
Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
ADROIT: Android malware detection using meta-information
  • Publication Type:
    Conference
  • Authors:
    Martín A, Calleja A, Menendez HD, Tapiador J, Camacho D
  • Publisher:
    IEEE
  • Publication date:
    13/02/2017
  • Published proceedings:
    Proceedings of the Symposium Series on Computational Intelligence (SSCI) 2016
  • ISBN-13:
    978-1-5090-4240-1
  • Status:
    Published
  • Name of conference:
    Symposium Series on Computational Intelligence (SSCI)
  • Conference place:
    Athens, Greece
  • Conference start date:
    06/12/2016
  • Conference finish date:
    09/12/2016
  • Language:
    English
  • Keywords:
    Androids, Humanoid robots, Malware, Text mining, Decision trees, Performance evaluation
Abstract
Android malware detection represents a current and complex problem, where black hats use different methods to infect users' devices. One of these methods consists in directly upload malicious applications to app stores, whose filters are not always successful at detecting malware, entrusting the final user the decision of whether installing or not an application. Although there exist different solutions for analysing and detecting Android malware, these systems are far from being sufficiently precise, requiring the use of third-party antivirus software which is not always simple to use and practical. In this paper, we propose a novel method called ADROIT for analysing and detecting malicious Android applications by employing meta-information available on the app store website and also in the Android Manifest. Its main objective is to provide a fast but also accurate tool able to assist users to avoid their devices to become infected without even requiring to install the application to perform the analysis. The method is mainly based on a text mining process that is used to extract significant information from meta-data, that later is used to build efficient and highly accurate classifiers. The results delivered by the experiments performed prove the reliability of ADROIT, showing that it is capable of classifying malicious applications with 93.67% accuracy.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Author
Dept of Computer Science
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by