Android malware detection technique via feature analysis

Ng, Ai Ping and Chiew, Kang Leng and Dayang Hanani, Binti Abang Ibrahim and Tiong, Wei King and Sze, San Nah and Nadianatra, binti Musa (2018) Android malware detection technique via feature analysis. Journal of Engineering Science and Technology, July. pp. 78-90. ISSN 1823-4690

Preview

PDF ANDROID MALWARE DETECTION TECHNIQUE VIA FEATURE ANALYSIS (abstract).pdf Download (514kB) | Preview

Abstract

The rapidly increasing popularity of the Android platform has resulted in a significant increase in the number of malware compared to previous years. Since Android offers an open market model, it is an ideal target to launch malware attacks. Due to this problem, a lot of research work has been proposed to protect users from attacks. However, such protection cannot last long as attackers will usually find ways to defeat protection mechanism. As a result, this paper aims to develop an effective malware detection technique. The proposed method focuses on static analysis approach, which utilizes features from permissions, intents and API calls of an Android application. In order to create a sensitive and representative feature set, the proposed method also uses the correlation-based feature selection method. The final feature set will be fed into the support vector machine to perform the classification. Experimental results have shown that the proposed method achieved reliable detection accuracy at 95% and outperformed the benchmark method

Actions (For repository members only: login required)

View Item