Digital networks and systems are susceptible to malicious software (malware) attacks. Deep learning (DL) models have recently emerged as effective methods to classify and detect malware. However, DL models often relies on gradient descent optimization in learning, i.e., the Back-Propagation (BP) algorithm; therefore, their training and optimization procedures suffer from several limitations, such as high computational cost and local suboptimal solutions. On the other hand, ensemble methods overcome the shortcomings of individual models by consolidating their strengths to increase performance. In this paper, we propose an ensemble-based parallel DL classifier for malware detection. In particular, a stacked ensemble learning method is developed, which leverages five DL base models and a neural network as a meta model. The DL models are trained and optimized with a hybrid optimization method based on BP and Particle Swarm Optimization (PSO) algorithms. To improve scalability and efficiency of the ensemble method, a parallel computing framework is exploited. The proposed ensemble method is evaluated using five malware datasets (namely, Drebin, NTAM, TOP-PE, DikeDataset, and ML_Android), and high accuracy rates of 99.2%, 99.3%, 98.7%, 100%, and 100% have been achieved, respectively. Its parallel implementation also significantly enhances the computational speed by a factor up to 6.75 times. These results ascertain that the proposed ensemble method is effective, efficient, and scalable, outperforming many other compared methods in malware detection.

Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs). These AEs are meticulously crafted by adversaries, introducing imperceptible perturbations to clean data to deceive DL models. Consequently, AEs pose potential risks to DL applications. In this paper, we propose an effective framework for enhancing the robustness of DL models against adversarial attacks. The framework leverages convolutional neural networks (CNNs) for feature learning, Deep Neural Networks (DNNs) with softmax for classification, and a defense mechanism to identify and exclude AEs. Evasion attacks are employed to create AEs to evade and mislead the classifier by generating malicious samples during the test phase of DL models i.e., CNN and DNN, using the Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and Square Attack (SA). A protection layer is developed as a detection mechanism placed before the DNN classifier to identify and exclude AEs. The detection mechanism incorporates a machine learning model, which includes one of the following: Fuzzy ARTMAP, Random Forest, K-Nearest Neighbors, XGBoost, or Gradient Boosting Machine. Extensive evaluations are conducted on the MNIST, CIFAR-10, SVHN, and Fashion-MNIST data sets to assess the effectiveness of the proposed framework. The experimental results indicate the framework’s ability to effectively and accurately detect AEs generated by four popular attacking methods, highlighting the potential of our developed framework in enhancing its robustness against AEs.

Among indoor positioning technologies, Wi-Fi fingerprinting using the Received Signal Strength Indicator (RSSI) is the most convenient and cost-effective method for indoor positioning. Instability and interference in wireless signal transmission cause significant variations in the RSSI, especially in a dynamic environment (DE). These factors hamper the accuracy of fingerprint-based indoor positioning system (IPSs), as these systems may struggle to reliably match observed signal patterns with stored fingerprints. Thus, ensuring positioning accuracy is critically important when designing and implementing Wi-Fi IPSs. Currently, there is a lack of surveys that provide a detailed and systematic analysis of the impact of DEs on the accuracy and reliability of Wi-Fi indoor positioning. This systematic literature review (SLR) was conducted to examine three aspects of Wi-Fi indoor positioning based on the RSSI: the impact of a DE on indoor positioning accuracy, the importance of constructing radio maps for indoor localization, and the role of machine learning (ML)/deep learning (DL) models in predicting indoor position with minimal error despite the DE. This review was conducted according to a structured and well-defined methodology to search for and filter relevant studies on Wi-Fi indoor positioning using the RSSI. Through this systematic process, 128 papers (2018–2024) were identified as relevant and then extracted and thoroughly analyzed to effectively answer the specified research questions. Additionally, this review highlights gaps in existing research, suggests directions for future studies, and provides practical recommendations for enhancing Wi-Fi-based indoor positioning in DEs.

Retrieval-Augmented Generation (RAG) is a hybrid method that combines information retrieval with large language models to generate context-aware, factually grounded responses. However, the RAG system relies heavily on well-structured input data to generate accurate and contextually relevant responses. Documents with complex table layouts pose significant challenges, as most chunking strategies are text-centric and often overlook table-rich documents containing multi-column and multi-row structures. Hence, this study proposes a customized structure-aware chunking framework specifically designed for university course documents containing multi-column, multi-row tables with nested headers. The framework employs Camelot for high-fidelity table extraction, followed by customized logic that constructs semantically coherent chunks by preserving academic term, subject name, credit hour, and category. This prevents semantic fragmentation during retrieval. The proposed method is evaluated using the RAGAS framework and compared against several baselines using standard parsing and chunking techniques. Results show that the proposed approach achieves the highest answer accuracy of 0.73 and substantially improves retrieval relevance and contextual precision. These findings demonstrate the framework’s effectiveness in handling structure-dependent academic queries. This study highlights that ensuring both parsing quality and chunking strategy is essential to retain semantic relationships in table-rich documents, offering a practical improvement for RAG systems in structurally complex scenarios.