Cyber-attacks have become a significant concern today, particularly in IoT environments where security poses a substantial challenge due to the distributed nature and heterogeneity of protocols. To efficiently detect threats in IoT networks, it is crucial to develop a robust intrusion-detection system (IDS) capable of identifying various modern and traditional attacks with high accuracy. Most existing machine-learning-based intrusion-detection systems for IoT have been trained using outdated datasets that do not accurately reflect IoT scenarios. Additionally, current research does not adequately address which machine-learning classifiers are most suitable for developing an efficient IDS in IoT environments. In our research, we have developed and trained a real-time intrusion-detection system for IoT networks that can detect multiple modern and traditional threats with high accuracy. We created seven instances of real-time IDS using state-of-the-art machine-learning algorithms, including Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Decision Tree, Random Forest, Naïve Bayes, and Artificial Neural Networks. Using the Pearson Correlation Coefficient, we extracted the most relevant features from the BoT–IoT dataset. After rigorous preprocessing, we used these data to train our algorithms. Our trained model, INIDS, is not only up to date and real-time but also capable of accurately identifying multiple categories of attacks specifically related to IoT networks. To achieve maximum accuracy, instead of selecting only one classifier, we evaluated seven advanced machine-learning algorithms and provided a comprehensive comparison of their performance and efficiency in the context of IoT networks. This analysis can guide future researchers in choosing the right machine-learning algorithms for developing IDS. We found that Random Forest is the most robust classifier for IoT-based network intrusion-detection systems, achieving an accuracy of 99.2%. The second-best performer is Naïve Bayes, with an accuracy of 98.8%.

Internet of things (IoT) has emerged as a quintessential paradigm of communication systems. Current literature introduces notion of a named data network for IoT (NDN-IoT), optimizing IoT communication by employing name-based networking. However, the advancements introduced by this approach are inadequate when dealing with URL-based naming and forwarding. For instance, length and ambiguities in content names are still open challenges. In addition, the intelligent exploration of content names to discern a forwarding clue is a significant research gap. To achieve intelligent communication, understanding the interest name and acquiring a forwarding clue is crucial. Focusing on this gap, an intelligent naming scheme called INF-NDN IoT is proposed that correlates with a forwarding mechanism as well. The proposed INF-NDN IoT improves the NDN naming schemas by utilizing natural language processing (NLP) techniques and selecting supernodes and ordinary nodes in the network. INF-NDN IoT assigns (forwarding clue) semantic tags to content names as well as to supernodes that in turn perform the semantic forwarding. Experimental results have shown that INF-NDN IoT outperformed existing work, and has better results in terms of name length, name memory utilization, interest satisfaction rate, retrieval time, hop count, and energy consumption.

Autonomous vehicles are revolutionizing the future of intelligent transportation systems by integrating smart and intelligent onboard units (OBUs) that minimize human intervention. These vehicles can communicate with their environment and one another, sharing critical information such as emergency alerts or media content. However, this communication infrastructure is susceptible to cyber-attacks, necessitating robust mechanisms for detection and defense. Among these, the most critical threat is the denial-of-service (DoS) attack, which can target any entity within the system that communicates with autonomous vehicles, including roadside units (RSUs), or other autonomous vehicles. Such attacks can lead to devastating consequences, including the disruption or complete cessation of service provision by the infrastructure or the autonomous vehicle itself. In this paper, we propose a system capable of detecting DoS attacks in autonomous vehicles across two scenarios: an infrastructure-based scenario and an infrastructureless scenario, corresponding to vehicle-to-everything communication (V2X) Mode 3 and Mode 4, respectively. For Mode 3, we propose an ensemble learning (EL) approach, while for the Mode 4 environment, we introduce a gossip learning (GL)-based approach. The gossip and ensemble learning approaches demonstrate remarkable achievements in detecting DoS attacks on the UNSW-NB15 dataset, with efficiencies of 98.82% and 99.16%, respectively. Moreover, these methods exhibit superior performance compared to existing schemes.

In-network caching stands as one of the core pillars of the named data networking (NDN) paradigm, where every internet router has the capability to store the incoming data packets in its cache along the path between data sources and consumers. This capability is particularly vital in Internet of Things (IoT) environments, where efficient and timely data retrieval is critical. Numerous strategies have been designed for caching IoT data and often rely on the exact match policy (EMP), which strictly matches content names for data retrieval. However, semantic considerations of content names in EMP remain underexplored. Additionally, several caching mechanisms are modeled after traditional IP-based communication approaches, such as neighbor or topology-based centrality methods for content placement and data eviction for replacement. These approaches hold limited relevance in NDN, as content names can originate from anywhere in the network. To this end, we propose a novel semantic-aware naming resolution as an alternative to EMP in cache design. Furthermore, the proposed scheme introduces a content-based centrality mechanism, along with a backup strategy for cache management. Integration of semantics into caching strategies offers a more optimal approach for supporting NDN IoT. This combination can boost overall network performance. Simulation results illustrate that the proposed scheme outperformed the advanced existing studies CaDaCa and PoolCache in cache hit ratios, semantic satisfaction rate, latency, and route elongation factor.

Unmanned aerial vehicles (UAVs) are critical for maintaining communication in disaster-affected areas, where terrestrial infrastructure is often unavailable and network connectivity becomes highly fragile. To address this challenge, this article proposes decentralized data forwarding and trajectory alignment in UAV-assisted networks using an information-centric paradigm. Specifically, we propose a mobility-aware QoS information-centric networking (MA-QoS ICN) framework, wherein each UAV embeds quality-of-service information (QoS info), including priority, deadline, and packet lifetime—as well as UAV mobility state information (UMSI), such as velocity, direction, position, and battery level, directly into the ICN packet headers. To model the dynamic and uncertain environment, we formulate the UAV coordination problem as a stochastic game for maximizing long-term content delivery performance, where each UAV acts as a learning agent and makes forwarding and trajectory alignment decisions based on its local state. We then develop a multiagent reinforcement learning (MARL) framework in which each UAV independently discovers its optimal strategy through local observations and experience, without requiring centralized control. In particular, we adopt an agent-independent learning method based on independent Q-learning, leveraging ICN’s packet-level handling for implicit coordination. This design significantly reduces communication overhead while preserving coordination among agents. Simulation results demonstrate that the proposed framework achieves substantial improvements in delivery reliability, latency reduction, and retransmission minimization, along with enhanced scalability under diverse disaster conditions.