作者: A. M. Aswini , P. Vinod
DOI: 10.1109/ICADIWT.2014.6814679
关键词:
摘要: In this paper, we propose static analysis of android malware files by mining prominent permissions. The proposed technique is implemented extracting permissions from 436 .apk files. Feature pruning carried out to investigate the impact feature length on accuracy. features that give way lesser misclassification are determined using Bi-Normal Separation (BNS) and Mutual Information (MI) selection techniques. Results suggest Droid permission miner can be used for preliminary classification Android package