Enhanced Federated Learning Framework based on Deep Learning and Neutrosophic Set for Android Malware Classification

Abstract

 Malware detection is one of the critical tasks of cybersecurity, especially considering the growing 
popularity of mobile devices. The integrity and security of mobile ecosystems rely on the capacity to 
identify malware quickly and precisely, as security hacks against these devices become increasingly 
frequent. Due to the requirement for massive volumes of data aggregation, traditional centralized machine 
learning (ML) techniques for malware detection face challenges with data sharing, computational 
complexity, and privacy. This research addresses these challenges by proposing a novel model, called 
"CNN-Fed", which is based on Convolutional Neural Networks (CNN) with Federated Learning (Fed). The 
main goal of this work is to create a global classifier for Android malware detection that is highly accurate 
and does not require centralised data aggregation. Using four benchmark datasets—Drebin, Malgenome, 
Kronodroid, and Tuandromd—the CNN-Fed model is trained across many clients in a federated setting 
under the suggested architecture. Then we use multi-criteria decision-making (MCDM) methodology to 
evaluate the number of clients and number of rounds. We use two MCDM methods such as Entropy 
methodology to compute the criteria weights and the CoCoSo methodology to rank the alternatives. We 
use the interval-valued neutrosophic sets (IVNSs) to deal with uncertainty and vague information. We use 
five criteria such as accuracy, F1-score, precision, recall, and FP and six of alternatives refer to the number 
of clients and number of rounds. The results show the best alternative has a larger number of clients and 
rounds. 

DOI: 10.5281/zenodo.15069485