ANDROID MALWARE DETECTION USING STATIC MALWARE ANALYSIS AND NATURAL LANGUAGE PROCESSING

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 uploading 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. We propose a novel method 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 becoming infected. 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 accurate classifiers.