Assistant Professor, Department of Computer Sciences, Golestan University, Gorgan, Iran
Abstract
This paper introduces a novel and hybrid framework for Android malware detection that integrates an Improved Particle Swarm Optimization (IPSO) algorithm with a Fuzzy Kernel Support Vector Machine (FKSVM). The primary key objective is to address the limitations of traditional methods, such as high feature dimensionality, premature convergence, and the inability to model the inherent uncertainty in malware data set. The IPSO algorithm employs a dynamic inertia weight and a random mutation operator to prevent premature convergence and to select an optimal feature subset. Subsequently, the FKSVM model, utilizing a novel fuzzy kernel, effectively handles data uncertainty. Evaluation of the proposed framework on the CIC-AndMal2020 data set demonstrates that it achieves 99.98% accuracy in binary classification and a very low false alarm rate of 0.01%. These results confirm the framework's superior performance compared to existing methods in terms of accuracy, speed, and robustness against adversarial attacks, validating its overall effectiveness.
Tajari Siahmarzkooh, A. (2026). A Hybrid Framework for Android Malware Detection Using Improved Particle Swarm Optimization and Fuzzy Kernel Support Vector Machine. Passive Defense, (), -.
MLA
Aliakbar Tajari Siahmarzkooh. "A Hybrid Framework for Android Malware Detection Using Improved Particle Swarm Optimization and Fuzzy Kernel Support Vector Machine", Passive Defense, , , 2026, -.
HARVARD
Tajari Siahmarzkooh, A. (2026). 'A Hybrid Framework for Android Malware Detection Using Improved Particle Swarm Optimization and Fuzzy Kernel Support Vector Machine', Passive Defense, (), pp. -.
VANCOUVER
Tajari Siahmarzkooh, A. A Hybrid Framework for Android Malware Detection Using Improved Particle Swarm Optimization and Fuzzy Kernel Support Vector Machine. Passive Defense, 2026; (): -.
)