Reliable and Secure Classification Techniques for Spotting Malware in Mobile

Pooja B. Kote, S. M. Rokade

Abstract: Nowadays there are many advanced techniques to hide from static and dynamic analysis tools in mobile. To get rid of this when attacking a mobile device an effective approach is required for the diagnosis of the application. In current approach to evaluate android app use of only simple code and pattern. The hacker can override this combination of diagnosis of pattern, as a result which may infect the device with the malware. This paper introduce approach which is using various techniques like patterns, flow based, behaviour based, state based and do analysis of each individual data by its associated specialized algorithms. The results obtained are fused to get the final results of that application. This paper aims to find malware using multi-classification technique. The algorithms will be used are Call Graph Based Classification, Neural network based Classification, and Naive Byes Based Classification. Experimental results show the feasibility and effectiveness of the proposed approach to detect the malware.

Keywords: android, call graph, malware detection, naive byes, neural network

How to Cite?: Pooja B. Kote, S. M. Rokade, "Reliable and Secure Classification Techniques for Spotting Malware in Mobile", Volume 6 Issue 6, June 2017, International Journal of Science and Research (IJSR), Pages: 671-673, https://www.ijsr.net/getabstract.php?paperid=ART20174219, DOI: https://dx.doi.org/10.21275/ART20174219