Phishing involves manipulating individuals into revealing private data, e.g., user IDs, bank details, and passwords. The observed surge in fraud is related to increased deception, impersonation, and advanced online attacks. Thus, effective phishing detection methods are required to mitigate escalating global phishing threats. Existing methods (e.g., heuristics-based, signature-based, and visual similarity-based methods) attempt to detect phishing sites, and machine learning (ML) and deep learning (DL) methods are effective in the cybersecurity context in terms of learning from data, offering insights, and forecasting. However, independent ML algorithms are limited when handling complex data, and DL techniques surpass traditional ML methods in terms of performance but require more data and time. To tackle these challenges, we present EnLeM, an ensemble learning model designed specifically for phishing website detection. EnLeM brings together three well-known machine learning classifiers—decision tree, random forest, and k-nearest neighbor—using a hard voting mechanism, and further strengthens efficiency with Mutual Information–based feature selection. When tested on the UCI phishing dataset, EnLeM delivered strong results, reaching 97.21% accuracy and a 97.51% F1-score. Compared to individual ML classifiers, it consistently performed better, and it also proved more efficient than deep learning models such as CNN and LSTM. Notably, EnLeM maintained stable accuracy across different feature subsets while cutting execution time by roughly 13%. By striking a balance between accuracy, speed, and interpretability, EnLeM stands out as a practical and scalable solution for real-time phishing detection without the heavy resource demands of deep learning approaches.

Transfer learning, a method that influences pretrained models to improve performance on new tasks, faces several data privacy, security, and scalability challenges when applied in decentralized environments. Recently, there have been few attempts to integrate blockchain technology with a transfer-learning approach. However, these classical blockchainbased non-collaborative transfer learning models face significant challenges, including poor scalability, security vulnerability, lack of data diversity, and inefficient incentive structures, thereby hindering the effectiveness and efficiency of the transfer learning process. This paper presents a unified framework that utilizes decentralized blockchain technology for collaborative transfer learning. The framework enables secure model sharing within a collaborative learning environment, supported by incentive mechanisms while maintaining model integrity and providing context protection. We perform extensive experimental studies with eight well-known large-scale and fine-grained image datasets. After initial transfer learning, incorporating collaborative learning via the decentralized blockchain network yielded promising results. The global model, after aggregating contributions from all entities, shows an impressive 6.8 % to 10.0 % accuracy improvement compared to individual baseline models. For blockchain implementation, we use the Rahasak blockchain as the ledger and its Aplos platform for a customized smart contract interface. Rahasak-CA, the certificate authority of the Rahasak blockchain, stores the digital certificates of peers in the transfer learning process. The system was deployed using Docker and Kubernetes, and evaluated on the proposed testbed.

The advent of 5G technology holds transformative potential, reshaping industries with its improved connectivity and communication. In this research paper, we conduct a thorough analysis of the performance and capabilities of an indoor 5G network within a controlled lab environment. Utilizing an Amarisoft Callbox as the 5G core, in conjunction with a Remote Radio Head (RRH) and user equipment (UEs), we evaluate network performance across downlink, and uplink transmissions, considering TCP and UDP protocols between the gNodeB and UE. Our examination encompasses essential metrics such as latency, data rate, and CPU usage, providing valuable insights into the system's suitability for diverse applications.

Human facial expressions are an essential and fundamental component for expressing the state of the human mind. The automatic analysis of these nonverbal facial expressions has become a fascinating and quite challenging problem in computer vision, with its application in different areas, such as psychology, human–machine interaction, health, and augmented reality. Recently, deep learning (DL) has become a widespread technique for studying human nonverbal facial sentiment expressions, and some research attempts have been made to propose a certain model on this topic. The purpose of this paper is to apply the appropriate convolutional neural network (CNN) approach by adding several layers of different dimensions, which allows the CNN approach to efficiently classify human facial sentiment expressions with data augmentation capable of recognizing seven basic human facial expressions: anger, sadness, fear, disgust, happiness, surprise, and neutral. In particular, this study mainly proposes a convolution neural network architecture, as well as learning factors that minimize the memory space and total training time of the proposed network due to the shallow architecture of the model. Following that, we demonstrated our proposed model’s network complexity, computational cost, and classification accuracy on the three benchmark datasets: FER2013, KDEF, and JAFFE. As a result, our proposed approach achieves accuracy of [Formula: see text], [Formula: see text], [Formula: see text] in the FER2013, KDEF, and JAFFE, respectively, which is better compared to other state-of-the-art approaches.

Recently, Personal Data Storage (PDS) has inaugurated a substantial change to the way people can store and control their personal data, by moving from a service-centric to a user-centric model. PDS offers individuals the capability to keep their data in a unique logical repository, that can be connected and exploited by proper analytical tools, or shared with third parties under the control of end users. Up to now, most of the research on PDS has focused on how to enforce user privacy preferences and how to secure data when stored into the PDS. In contrast, in this paper we aim at designing a Privacy-aware Personal Data Storage (P-PDS), that is, a PDS able to automatically take privacy-aware decisions on third parties access requests in accordance with user preferences. The proposed P-PDS is based on preliminary results presented in [1] , where it has been demonstrated that semi-supervised learning can be successfully exploited to make a PDS able to automatically decide whether an access request has to be authorized or not. In this paper, we have deeply revised the learning process in order to have a more usable P-PDS, in terms of reduced effort for the training phase, as well as a more conservative approach w.r.t. users privacy, when handling conflicting access requests. We run several experiments on a realistic dataset exploiting a group of 360 evaluators. The obtained results show the effectiveness of the proposed approach.

The concept of Personal Data Storage (PDS) has recently emerged as an alternative and innovative way of managing personal data w.r.t. the service-centric one commonly used today. The PDS offers a unique logical repository, allowing individuals to collect, store, and give access to their data to third parties. The research on PDS has so far mainly focused on the enforcement mechanisms, that is, on how user privacy preferences can be enforced. In contrast, the fundamental issue of preference specification has been so far not deeply investigated. In this paper, we do a step in this direction by proposing different learning algorithms that allow a fine-grained learning of the privacy aptitudes of PDS owners. The learned models are then used to answer third party access requests. The extensive experiments we have performed show the effectiveness of the proposed approach.