Since the development of information systems during the last decade, cybersecurity has become a critical concern for many groups, organizations, and institutions. Malware applications are among the commonly used tools and tactics for perpetrating a cyberattack on Android devices, and it is becoming a challenging task to develop novel ways of identifying them. There are various malware detection models available to strengthen the Android operating system against such attacks. These malware detectors categorize the target applications based on the patterns that exist in the features present in the Android applications. As the analytics data continue to grow, they negatively affect the Android defense mechanisms. Since large numbers of unwanted features create a performance bottleneck for the detection mechanism, feature selection techniques are found to be beneficial. This work presents a Rock Hyrax Swarm Optimization with deep learning-based Android malware detection (RHSODL-AMD) model. The technique presented includes finding the Application Programming Interfaces (API) calls and the most significant permissions, which results in effective discrimination between the good ware and malware applications. Therefore, an RHSO based feature subset selection (RHSO-FS) technique is derived to improve the classification results. In addition, the Adamax optimizer with attention recurrent autoencoder (ARAE) model is employed for Android malware detection. The experimental validation of the RHSODL-AMD technique on the Andro-AutoPsy dataset exhibits its promising performance, with a maximum accuracy of 99.05%.
The Internet of Things or “IoT” determines the highly interconnected network of heterogeneous devices where each type of communication seems to be possible, even unauthorized. Consequently, the security requirement for these networks became crucial, while conventional Internet security protocol was identified as unusable in these types of networks, especially because of some classes of IoT devices with constrained resources. Secure group communication (SGC) in the IoT environment is vital to ensure the confidentiality, integrity, and availability (CIA) of data swapped within a collection of IoT devices. Typically, IoT devices were resource-constrained with limited memory, processing, energy, and power, which makes SGC a difficult task. This article designs a Fully Homomorphic Encryption with Optimal Key Generation Secure Group Communication (FHEOKG-SGC) technique in the IoT environment. The presented FHEOKG-SGC technique mainly focuses on the encryption and routing of data securely in the IoT environment via group communication. To accomplish this, the presented FHEOKG-SGC technique initially designs an FHE-based encryption technique to secure the data in the IoT environment. Next, the keys in the FHE technique are chosen optimally using the sine cosine algorithm (SCA). At the same time, the plum tree algorithm (PTA) is applied for the identification of the routes in the IoT network. Finally, the FHEOKG-SGC technique employs a trust model to improve the secure communication process, and the key management center is used for optimal handling of the keys. The simulation analysis of the FHEOKG-SGC technique is tested using a series of experiments, and the outcomes are studied under various measures. An extensive comparative study highlighted the improvement of the FHEOKG-SGC algorithm over other recent approaches.
8 May 2024 in International Journal of Communication Systems
Number recognition can be an important and necessary challenge because handwritten numbers are not similar in size, thickness, position and direction; this method should consider different difficulties to deal with the difficulty of recognizing written numbers. Individuality and assortment in the composition of varieties of different people additionally affect the instance and availability of numbers. It is a process for selecting and composing translated numbers. It's a wide variety of apps, such as programmed arrays, contact points and income related documents, and then beyond. The objective of this work is to implement an algorithmic classification rule for recognizing written numbers. Sometime consequences are probably used various machine learning algorithms like K-means nereast neural networks (KNN), Support vector machine (SVM), KNN and Deep Learning calculations using keras, tensorflow and CNN classifier. The simulation accuracy is 98.70% obtained using CNN and compared with SVM 97%, KNN is 96% and keras as 96%.