Android malware classification based on random vector functional link and artificial Jellyfish Search optimizer

Abstract

Smartphone usage is nearly ubiquitous worldwide, and Android provides the leading open-source operating system, retaining the most significant market share and active user population of all open-source operating systems. Hence, malicious actors target the Android operating system to capitalize on this consumer reliance and vulnerabilities present in the system. Hackers often use confidential user data to exploit users for advertising, extortion, and theft. Notably, most Android malware detection tools depend on conventional machine-learning algorithms; hence, they lose the benefits of metaheuristic optimization. Here, we introduce a novel detection system based on optimizing the random vector functional link (RVFL) using the artificial Jellyfish Search (JS) optimizer following dimensional reduction of Android application features. JS is used to determine the optimal configurations of RVFL to improve classification performance. RVFL+JS minimizes the runtime of the execution of the optimized models with the best performance metrics, based on a dataset consisting of 11,598 multi-class applications and 471 static and dynamic features.

Block Chain Technology Assisted Privacy Preserving Resource Allocation Scheme for Internet of Things Based Cloud Computing

“…End while End Tizhoosh developed Opposition-based learning (OBL). The discoverer of OBL says that a number opposite was possibly nearer than an arbitrary number to solutions [19]. By incorporating OBL in traditional evolutionary approaches, one might raise the coverage of solution space important to faster convergence and increased accuracy.…”

Random vector functional link network: recent developments, applications, and future directions

“…To address the instability issue in the sliding mode control system, Zhou and Wu [97] proposed an adaptive fuzzy RVFL (FRVFL), wherein self-mapping between fuzzy rules and hidden layers is employed and adaptive rules are also employed to achieve self-adjustment for the output weights. To address the threats issues in android malware detection tools, in [98], a novel technique using RVFL model with artificial jellyfish search (JS) optimizer algorithm for selecting the optimal features of android malware datasets, i.e., RVFL+JS, has been proposed. The JS algorithm reduces the redundant and irrelevant features from the data that handle the storage and time complexity issue and hence, improves the generalization performance of the RVFL+JS model.…”

Recent advances in use of bio-inspired jellyfish search algorithm for solving optimization problems

“…Elkabbash et al 104 proposed a novel detection system that was based on optimizing the random vector functional link (RVFL) using JSO, following the dimensional reduction of Android application features. They used JSO to determine the optimal configurations of RVFL to improve classification performance.…”

“…Optimizing hyper-parameters of deep learning JSO Chou et al 102 Optimizing hyper-parameters of LSSVR JSO-LSSVR Chou and Truong 88 Estimating parameters of a single-phase power transformer JSO Youssef et al 106 Optimizing parameters of solar photovoltaic (PV) model JSO Bisht and Sikander 108 Finding optimal coefficients of DWT JSO Dhevanandhini and Yamuna 103 Finding optimal configurations of RVFL JSO Elkabbash et al 104 Identification of parameters of PEMFCs JSO Gouda et al (1) Self-adaption: adaptive or self-adaptive algorithms are those that can self-tune their algorithm-specific and common control parameters. The algorithm-specific parameters in JSO include the number of iterations, population size, spatial distribution coefficients, and motion coefficients.…”