The Internet of Things (IoT) is an innovation that combines imagined space with the actual world on a single platform. Because of the recent rapid rise of IoT devices, there has been a lack of standards, leading to a massive increase in unprotected devices connecting to networks. Consequently, cyberattacks on IoT are becoming more common, particularly keylogging attacks, which are often caused by security vulnerabilities on IoT networks. This research focuses on the role of transfer learning and ensemble classifiers in enhancing the detection of keylogging attacks within small, imbalanced IoT datasets. The authors propose a model that combines transfer learning with ensemble classification methods, leading to improved detection accuracy. By leveraging the BoT-IoT and keylogger_detection datasets, they facilitate the transfer of knowledge across various domains. The results reveal that the integration of transfer learning and ensemble classifiers significantly improves detection capabilities, even in scenarios with limited data availability. The proposed TRANS-ENS model showcases exceptional accuracy and a minimal false positive rate, outperforming current deep learning approaches. The primary objectives include: (i) introducing an ensemble feature selection technique to identify common features across models, (ii) creating a pre-trained deep learning model through transfer learning for the detection of keylogging attacks, and (iii) developing a transfer learning-ensemble model dedicated to keylogging detection. Experimental findings indicate that the TRANS-ENS model achieves a detection accuracy of 96.06% and a false alarm rate of 0.12%, surpassing existing models such as CNN, RNN, and LSTM.

Internet Exchange Point (IXP) is a system that increases network bandwidth performance. Internet exchange points facilitate interconnection among network providers, including Internet Service Providers (ISPs) and Content Delivery Providers (CDNs). To improve service management, Internet exchange point providers have adopted the Software Defined Network (SDN) paradigm. This implementation is known as a Software-Defined Exchange Point (SDX). It improves network providers’ operations and management. However, performance issues still exist, particularly with multi-hop topologies. These issues include switch memory costs, packet processing latency, and link failure recovery delays. The paper proposes Enhanced Link Failure Rerouting (ELFR), an improved mechanism for rerouting link failures in software-defined exchange point networks. The proposed mechanism aims to minimize packet processing time for fast link failure recovery and enhance path calculation efficiency while reducing switch storage overhead by exploiting the Programming Protocol-independent Packet Processors (P4) features. The paper presents the proposed mechanisms’ efficiency by utilizing advanced algorithms and demonstrating improved performance in packet processing speed, path calculation effectiveness, and switch storage management compared to current mechanisms. The proposed mechanism shows significant improvements, leading to a 37.5% decrease in Recovery Time (RT) and a 33.33% decrease in both Calculation Time (CT) and Computational Overhead (CO) when compared to current mechanisms. The study highlights the effectiveness and resource efficiency of the proposed mechanism in effectively resolving crucial issues in multi-hop software-defined exchange point networks.