Visible to the public Andro-Simnet: Android Malware Family Classification Using Social Network Analysis

TitleAndro-Simnet: Android Malware Family Classification Using Social Network Analysis
Publication TypeConference Paper
Year of Publication2018
AuthorsKim, H. M., Song, H. M., Seo, J. W., Kim, H. K.
Conference Name2018 16th Annual Conference on Privacy, Security and Trust (PST)
ISBN Number978-1-5386-7493-2
KeywordsAndro-Simnet, Android (operating system), Android malware family classification, behavior-based detection, Classification algorithms, detection algorithms, efficient malware classification, feature extraction, Generators, graph visualization, high classification accuracy, Human Behavior, invasive software, k-fold cross-validation, machine learning, Malware, malware classification, malware dataset, malware family network aggregation, malware similarity, malwares attack behavior pattern, metamorphic malware, Metrics, mobile computing, mobile devices, pattern classification, polymorphic malware, privacy, pubcrawl, resilience, Resiliency, signature-based malware detection method, social network analysis, Social network services, social networking (online), static analysis, tactical characteristics

While the rapid adaptation of mobile devices changes our daily life more conveniently, the threat derived from malware is also increased. There are lots of research to detect malware to protect mobile devices, but most of them adopt only signature-based malware detection method that can be easily bypassed by polymorphic and metamorphic malware. To detect malware and its variants, it is essential to adopt behavior-based detection for efficient malware classification. This paper presents a system that classifies malware by using common behavioral characteristics along with malware families. We measure the similarity between malware families with carefully chosen features commonly appeared in the same family. With the proposed similarity measure, we can classify malware by malware's attack behavior pattern and tactical characteristics. Also, we apply community detection algorithm to increase the modularity within each malware family network aggregation. To maintain high classification accuracy, we propose a process to derive the optimal weights of the selected features in the proposed similarity measure. During this process, we find out which features are significant for representing the similarity between malware samples. Finally, we provide an intuitive graph visualization of malware samples which is helpful to understand the distribution and likeness of the malware networks. In the experiment, the proposed system achieved 97% accuracy for malware classification and 95% accuracy for prediction by K-fold cross-validation using the real malware dataset.

Citation Keykim_andro-simnet:_2018