Intelligent Hybrid Approach for Android Malware Detection based on Permissions and API Calls

摘要: Android malware is rapidly becoming a potential threat to users. The number of growing exponentially; they become significantly sophisticated and cause financial information losses for Hence, there need effective efficient techniques detect the applications. This paper proposes an intelligent hybrid approach detection using permissions API calls in application. proposed consists two steps. first step involves finding most significant Application Programming Interfaces (API) that leads discrimination between good ware For this purpose, features selection algorithms, Information Gain (IG) Pearson CorrCoef (PC) are employed rank individual API’s based on their importance classification. In second step, new combination Adaptive neural fuzzy Inference System (ANFIS) with Particle Swarm Optimization (PSO), differentiate goodware applications (apps). PSO intelligently utilized optimize ANFIS parameters by tuning its membership functions generate reliable more precise rules apps Using dataset 250 collected from different recourse, conducted experiments show suggested method achieved accuracy 89%.