This study investigates the robustness of deep learning-based steganalysis models against common image transformations because most literature has not paid enough attention to resilience assessment. Current and future applications of steganalysis to guarantee digital security are gaining importance regarding real-world modifications: resizing, compression, cropping, and adding noise. These included the following five basic models: EfficientNet, SRNet, ResNet, Xu-Net, and Yedroudj-Net. We evaluated these models' pre- and post-transformation performances based on various metrics like accuracy, precision, recall, F1-score, and AUC with the BOSSBase dataset. Our results showed that EfficientNet is the most robust among the considered architecture transformations. Still, it also underlined significant degradations for state-of-the-art models, Xu-Net and Yedroudj-Net, especially with added noise. These results indicate the need to develop more robust architectures capable of sustaining real-world image alterations. In practice, it will assist practitioners in choosing models that best suit operational environments and lay the necessary platform for future enhancements in the design of such models. In this regard, in the future, more transformations should be researched with ensemble and adaptive approaches to improve robustness further.
The study was necessitated by the unprecedented consumption of smart devices by children in Saudi Arabia, which has been a concern to parents and other stakeholders. It investigated the way that game apps, social media apps, and video-streaming apps impact child development. It also examined the roles played by artificial intelligence control and parental control in enhancing the sustainability of children’s behavior amidst smart technologies. The theories underpinning this research were the theory of reasoned action and the theory of planned behavior. The population of the study was 1,616,755 households in the eastern, western, and central regions. The researcher used an online survey to capture the sentiments of a sample of 415 parents who had given their children at least one smart device. The primary questionnaire focused on game apps, social media apps, video-streaming apps, artificial intelligence control, parental control, and the sustainability of child behavior. On the other hand, a separate questionnaire designed specifically to capture demographic information was also drafted. The structural equation model (SEM) was preferred, as it depicted the moderating roles of artificial intelligence control and parental control by using SPSS AMOS software. Findings established that games, social media, and video-streaming applications negatively affected the sustainability of child behavior. The findings presented in this paper show that the moderating effect of artificial intelligence control was more statistically significant than parental controls in influencing the sustainability of child behavior. Moreover, the results show that the greatest effect on children’s behavior were social media, video-streaming, and games apps. respectively. Nevertheless, both approaches resulted in positive child behavior. Hence, the study concluded that using artificial intelligence control is more effective than relying on parental controls to enhance the behavioral sustainability of children with smart device applications in Saudi Arabia.
One of the key problems of the modern day is the presentation of an identity verification system that can perform sufficient accuracy in identity verification, is resilient to assaults and noises, and can be recorded in the simplest possible method. In this study, a new speaker feature extraction which based on discrete wavelet transform (DWT) and linear prediction coding (LPC) algorithm (WLPCA) are investigated. This paper's primary objective is to evidence the performance of the new method for speaker identification by a Gaussian mixture model (GMM). The proposed method improves the recognition rate over the Mel-frequency cepstral coefficient (MFCC). Experimental evaluation of the process performance is performed on two speech databases; our recorded database and the publicly available TIMIT database. We show that the speech features derived by the newly proposed method are more suitable for GMM (91.53%), in terms of the time-consumed, by requiring less Gaussian mixtures than MFCC (85.77%). For testing the presented method in a noisy environment, Additive white Gaussian noise (AWGN) was added to the TIMIT database, where a slight improvement in the performance of the presented method (60.02%) over the MFCC (59.89%) was observed.