A Two-Tier Fuzzy Meta-Heuristic Hybrid Optimization for Dynamic Android Malware Detection  

作　　者：K.Santosh Jhansi Sujata Chakravarty P.Ravi Kiran Varma 

机构地区：[1]Centurion University of Technology and Management,Paralakhemundi,Odisha,India [2]Maharaj Vijayaram Gajapathi Raj College of Engineering,Viizianagaram,India [3]Centurion University of Technology and Management,Bhubaneswar,Odisha,India

出　　处：《Journal of Cyber Security》2022年第3期185-202,共18页网络安全杂志（英文）

摘　　要：Application Programming Interface(API)call feature analysis is the prominent method for dynamic android malware detection.Standard benchmark androidmalware API dataset includes featureswith high dimensionality.Not all features of the data are relevant,filtering unwanted features improves efficiency.This paper proposes fuzzy and meta-heuristic optimization hybrid to eliminate insignificant features and improve the performance.In the first phase fuzzy benchmarking is used to select the top best features,and in the second phase meta-heuristic optimization algorithms viz.,Moth Flame Optimization(MFO),Multi-Verse Optimization(MVO)&Whale Optimization(WO)are run with Machine Learning(ML)wrappers to select the best from the rest.Five ML methods viz.,Decision Tree(DT),Random Forest(RF),K-NearestNeighbors(KNN),Naie Bayes(NB)&NearestCentroid(NC)are compared as wrappers.Several experiments are conducted and among them,the best post reduction accuracy of 98.34% is recorded with 95% elimination of features.The proposed novelmethod outperformed among the existing works on the same dataset.

关 键 词：Wrapper feature selection multi-verse optimization moth flame optimization whale optimization malware detection classification 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]