Malicious iOS apps detection through Multi-Criteria Decision-Making Approach

Abstract

Abstract Smartphones are used in daily lives because they are ubiquitous and provide internet connectivity. Their functionalities can be extended by installing third-party apps. Users are compelled to use these feature-rich apps. As a result, the menaces because of these apps have increased. Smartphones store more users’ personal than compared to data stored on desktops since they remain with individuals throughout the day making them an easy target for intruders. Apple follows permission-based access control to prevent users’ privacy. Every app declares the permission, which is notified to the user during app usage. However, the users are unaware of whether the app is breaching their privacy? To combat this problem, we propose a hybrid approach to detect malicious iOS apps based on their permissions. In the first phase, weights have been assigned to app permissions using a multi-criteria decision-making approach namely Analytic Hierarchy Process (AHP). In the second phase, machine and ensemble learning techniques have been employed for detecting malicious apps. To test the efficacy of the proposed method dataset comprising 1150 apps from 12 app categories has been used. The experimental results demonstrate the proposed approach improves the efficacy of detecting malicious iOS apps for majority of categories.