Industrial control systems (ICSs), supervisory control and data acquisition (SCADA) systems, and distributed control systems (DCSs) are fundamental components of critical infrastructure (CI). CI supports the operation of transportation and health systems, electric and thermal plants, and water treatment facilities, among others. These infrastructures are not insulated anymore, and their connection to fourth industrial revolution technologies has expanded the attack surface. Thus, their protection has become a priority for national security. Cyber-attacks have become more sophisticated and criminals are able to surpass conventional security systems; therefore, attack detection has become a challenging area. Defensive technologies such as intrusion detection systems (IDSs) are a fundamental part of security systems to protect CI. IDSs have incorporated machine learning (ML) techniques that can deal with broader kinds of threats. Nevertheless, the detection of zero-day attacks and having technological resources to implement purposed solutions in the real world are concerns for CI operators. This survey aims to provide a compilation of the state of the art of IDSs that have used ML algorithms to protect CI. It also analyzes the security dataset used to train ML models. Finally, it presents some of the most relevant pieces of research on these topics that have been developed in the last five years.

Communications from remote areas that may be of interest is still a problem. Many innovative projects applied to remote sites face communications difficulties. The GOLDFISH project was an EU-funded project for river pollution monitoring in developing countries. It had several sensor clusters, with floating WiFi antennas, deployed along a downstream river’s course. Sensor clusters sent messages to a Gateway installed on the riverbank. This gateway sent the messages, through a backhaul technology, to an Internet server where data was aggregated over a map. The communication challenge in this scenario was produced by the antennas’ movement and network backhaul availability. Since the antennas were floating on the river, communications could be disrupted at any time. Also, 2G/3G availability near the river was not constant. For non-real-time applications, we propose a Delay/Disruption Tolerant Network (DTN)-based solution where all nodes have persistent storage capabilities and DTN protocols to be able to wait minutes or hours to transmit. A mechanical backhaul will periodically visit the river bank where the gateway is installed and it will automatically collect sensor data to be carried to an Internet-covered spot. The proposed forwarding protocol delivers around 98% of the messages for this scenario, performing better than other well-known DTN routing protocols.

Internet of Things (IoT) networks have been integrated into industrial infrastructure schemes, positioning themselves as devices that communicate highly classified information for the most critical companies of world nations. Currently, and in order to look for alternatives to mitigate this risk, solutions based on Blockchain algorithms and Machine Learning techniques have been implemented separately with the aim of mitigating potential threats in IIoT networks. In this paper, we sought to integrate the previous solutions to create an integral protection mechanism for IoT device networks, which would allow the identification of threats, activate secure information transfer mechanisms, and it would be adapted to the computational capabilities of industrial IoT. The proposed solution achieved the proposed objectives and is presented as a viable mechanism for detecting and containing intruders in an IoT network. In some cases, it overcomes traditional detection mechanisms such as an IDS.

Traditional security detection methods face challenges in identifying zero-day attacks in critical infrastructures (CIs) integrated with the industrial internet of things (IIoT). These attacks exploit unknown vulnerabilities and are difficult to detect due to their connection to physical systems. The integration of legacy ICS networks with modern computing and networking technologies has significantly expanded the attack surface, making these systems more susceptible to cyber-attacks. Despite existing security measures, attackers continually find ways to breach these operating networks. Anomaly detection systems are critical in protecting these CIs from current cyber threats. This study investigates the effectiveness of unsupervised anomaly detection models in detecting operational anomalies that could lead to cyber-attacks, thereby disrupting and negatively impacting quality of life. We preprocess the data with a focus on cybersecurity and chose the SWAT dataset because it accurately represents the types of attack vectors that critical infrastructures commonly encounter. We evaluated the performance of isolation forest (IF), local outlier factor (LOF), one-class SVM (OCSVM), and Autoencoder algorithms—trained exclusively on normal data—in enhancing cybersecurity within IIoT environments. Our comprehensive analysis includes an assessment of each model’s detection capabilities. The findings highlight the VAE-LSTM model’s potential to identify cyber-attacks within seconds in a high-frequency dataset, suggesting near real-time detection capability. The final model combines the reconstruction ability of the variational autoencoder (VAE) with regularization using the Kullback–Leibler divergence, reflecting the non-Gaussian nature of industrial system data. Our model successfully detected 23 out of 26 attack scenarios in the SWAT dataset, demonstrating its effectiveness in improving the security of IIoT-based CIs.

The Internet of Things is a new paradigm in which objects in a specific context can be integrated into traditional communication networks to actively participate in solving a determined problem. The Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) technologies are specific cases of IoT and key enablers for Intelligent Transportation Systems (ITS). V2V and V2I have been widely used to solve different problems associated with transportation in cities, in which the most important is traffic congestion. A high percentage of congestion is usually presented by the inappropriate use of resources in vehicular infrastructure. In addition, the integration of traffic congestion in decision making for vehicular traffic is a challenge due to its high dynamic behavior. In this paper, an optimization model over the load balancing in the congestion percentage of the streets is formulated. Later, we explore a fully congestion-oriented route discovery mechanism and we make a proposal on the communication infrastructure that should support it based on V2I and V2V communication. The mechanism is also compared with a modified Dijkstra’s approach that reacts at congestion states. Finally, we compare the results of the efficiency of the vehicle’s trip with the efficiency in the use of the capacity of the vehicular network.

In recent years, there has been an exponential growth of IoT (Internet of Things) devices in the market and increasingly, they are being part of critical mission functionalities for many industries. For this reason, processes associated with these devices are generating new requirements at the level of interconnectivity, security, and scalability. Due to the large volume of devices, this growth process has tested the existing communications infrastructure, deployment architecture, different support services, technical requirements and the intrinsic characteristics of the services offered. In this sense, the use of Edge Computing schemes and TSN networks (Time Sensitive Networks), is proposed as a tool for supporting IIoT (Industrial Internet of Things) services to achieve optimization and assurance processes of latency, scalability and interoperability parameters required by critical mission services such as health, transportation and production. In this sense, we propose several strategies for assuring low latency, scalability and interoperability in Edge Computing and TSN networks for critical IIoT services. These strategies are evaluated considering different levels of congestion and considering different schemes such as best effort, TSN and Edge Computing.