Detecting Android Malwares with High-Efficient Hybrid Analyzing Methods

摘要: In order to tackle the security issues caused by malwares of Android OS, we proposed a high-efficient hybrid-detecting scheme for malwares. Our employed different analyzing methods (static and dynamic methods) construct flexible detecting scheme. this paper, some techniques such as Com+ feature based on traditional Permission API call features improve performance static detection. The collapsing issue function graph-based malware detection was also avoided, adopted selection clustering method unify graph various dimensions into same dimension. verify our scheme, built an open-access dataset in experiments. experimental results showed that suggested achieved high malware-detecting accuracy, could be used establish cloud services, which can automatically adopt high-efficiency according properties applications.