Intrusion detection systems (IDS) stand as formidable guardians in network security, playing a pivotal role in identifying and mitigating potential threats. As our digital landscape evolves, the imperative for robust intrusion detection mechanisms grows exponentially. The significance of IDS extends beyond preserving the integrity, confidentiality, and availability of network resources. In the dynamic realm of evolving cyber threats, IDS acts as the frontline defender-constantly monitoring network traffic to pinpoint suspicious activities and preemptively mitigate security breaches. In this paper, we study the effectiveness of combining the potency of the transformer-based model known as Bidirectional Encoder Representations from Transformers (BERT) in conjunction with the Synthetic Minority Over-sampling Technique (SMOTE) and a Multi-Layer Perceptron (MLP) to enhance the classification tasks in Machine Learning (ML) based IDS. We tested our approach on well-known and recent datasets, demonstrating that it is possible to obtain very high accuracy and robust performance in the detection of various attack types even when the datasets are affected by class imbalance. Beyond these results, our research introduces a novel perspective by seamlessly integrating the interpretability and context awareness of BERT with the efficient classification of MLP. This novel approach holds promise for advancing intrusion detection capabilities and contributing to the broader cybersecurity community.

5G targets to offer a huge network capacity to support the expected unprecedented traffic growth due mainly to mobile and machine-type services. Thus, the 5G access network has to comply with very challenging architectural requirements. Mobile network scalability is achieved by playing appropriately with the centralization of network functions and by applying the functional split introducing the fronthaul. Although more advantageous in terms of network management and performance optimization, low-layer functional split options require larger bandwidth and lower latency to be guaranteed by the fronthaul in the access network, while preserving other concurrent fiber-to-the-x services. Thus, advanced mechanisms for the efficient management of available resources in the access network are required to control jointly both radio and optical domains. Softwarized mobile and optical segments facilitate the introduction of dedicated protocols to enable the inter-working of the two control planes. This paper proposes a new cooperation scheme to manage the adaptive flexible functional split in 5G networks conditioned to the resource availability in the optical access network. Techniques for the accurate estimation of available bandwidth and the associated real-time selection of the best suitable functional split option are investigated. Results show that the proposed software defined converged approach to wavelength and bandwidth management guarantees the optimal allocation of optical resources. The triple exponential smoothing forecasting technique enables efficient coexistence of mobile fronthaul and fixed connectivity traffic in the network, reducing traffic impairments with respect to other well-known forecasting techniques, while keeping the same level of centralization.

The 5th generation of mobile networks has come to the market bringing the promise of disruptive performances as low latency, availability and reliability, imposing the development of the so-called “killer applications”. This contribution presents a 5G use case in the context of Structural Health Monitoring which guarantees an unprecedented level of reliability when exploited for public safety purposes as Earthquake Early Warning. The interest on this topic is at first justified through a deep market analysis, and subsequently declined in terms of public safety benefits. A specific sensor board, guaranteeing real-time processing and 5G connectivity, is presented as the foundation on which the architecture of the network is designed and developed. Advantages of 5G-enabled urban safety are then discussed and proven in the experimentation results, showing that the proposed architecture guarantees lower latency delays and overcome the impairments of cloud solutions especially in terms of delays variability.

This work presents a service for the improvement of cultural heritage experiences, which exploits the advantages coming from the 5G paradigm. Indeed, in a scenario where many users need to be served by a real-time solution which is in turn required to work on different devices, the potentialities of 5G technology show their suitability. In particular, moving the computation to the edge of the network ensures the availability of resources needed for binaural spatial audio rendering in an independent fashion with reference to the client device and at the same time it guarantees real-time availability of this data since the core network, with its impairments, is not involved. This work demonstrates how 5G could be a critical enabler for delivering low latency services at guaranteed levels, data-centric services, differentiated customer experiences, improved security and reduced costs to the users.

Digital Twins (DT) models are gaining special attention in the management and maintenance of facilities. The quality of data contained in these models may be enhanced by the use of processed information coming from long-term Structural Health Monitoring (SHM). In this case real time processing and updating in systems using sensor networks for SHM need low latency and reliable communication. This paper presents a solution for exploiting DT models for SHM and early warning solutions improvement. The case study scenario resides within the 5G experimentation in the city of L’Aquila and it exploits a highly adaptable sensor board and a 5G Multi-Access Edge Computing architecture.