Current quantum key distribution (QKD) networks focus almost exclusively on transporting secret keys at the highest possible rate. Consequently, they are built as mostly fixed, ad hoc, logically, and physically isolated infrastructures designed to avoid any penalty to the quantum channel. This architecture is neither scalable nor cost-effective and future, real-world deployments will differ considerably. The structure of the MadQCI QKD network presented here is based on disaggregated components and modern paradigms especially designed for flexibility, upgradability, and facilitating the integration of QKD in the security and telecommunications-networks ecosystem. These underlying ideas have been tested by deploying many QKD systems from several manufacturers in a real-world, multi-tenant telecommunications network, installed in production facilities and sharing the infrastructure with commercial traffic. Different technologies have been used in different links to address the variety of situations and needs that arise in real networks, exploring a wide range of possibilities. Finally, a set of realistic use cases has been implemented to demonstrate the validity and performance of the network. The testing took place during a period close to three years, where most of the nodes were continuously active.

Nowadays, malware has become an epidemic problem. Among the attacks exploiting the computer resources of victims, one that has become usual is related to the massive amounts of computational resources needed for digital currency cryptomining. Cybercriminals steal computer resources from victims, associating these resources to the crypto-currency mining pools they benefit from. This research work focuses on offering a solution for detecting such abusive cryptomining activity, just by means of passive network monitoring. To this end, we identify a new set of highly relevant network flow features to be used jointly with a rich set of machine and deep-learning models for real-time cryptomining flow detection. We deployed a complex and realistic cryptomining scenario for training and testing machine and deep learning models, in which clients interact with real servers across the Internet and use encrypted connections. A complete set of experiments were carried out to demonstrate that, using a combination of these highly informative features with complex machine learning models, cryptomining attacks can be detected on the wire with telco-grade precision and accuracy, even if the traffic is encrypted.

Network Digital Twin (NDT) is a new technology that builds on the concept of Digital Twins (DT) to create a virtual representation of the physical objects of a telecommunications network. NDT bridges physical and virtual spaces to enable coordination and synchronization of physical parts while eliminating the need to directly interact with them. There is broad consensus that Artificial Intelligence (AI) and Machine Learning (ML) are among the key enablers to this technology. In this work, we present B5GEMINI, which is an NDT for 5G and beyond networks that makes an extensive use of AI and ML. First, we present the infrastructural and architectural components that support B5GEMINI. Next, we explore four paradigmatic applications where AI/ML can leverage B5GEMINI for building new AI-powered applications. In addition, we identify the main components of the AI ecosystem of B5GEMINI, outlining emerging research trends and identifying the open challenges that must be solved along the way. Finally, we present two relevant use cases in the application of NDTs with an extensive use of ML. The first use case lays in the cybersecurity domain and proposes the use of B5GEMINI to facilitate the design of ML-based attack detectors and the second addresses the design of energy efficient ML components and introduces the modular development of NDTs adopting the Digital Map concept as a novelty.

This paper introduces an approach toward the automatic enforcement of security policies in network functions virtualization (NFV) networks and dynamic adaptation to network changes. The approach relies on a refinement model that allows the dynamic transformation of high-level security requirements into configuration settings for the network security functions (NSFs), and optimization models that allow the optimal selection of the NSFs to use. These models are built on a formalization of the NSF capabilities, which serves to unequivocally describe what NSFs are able to do for security policy enforcement purposes. The approach proposed is the first step toward a security policy aware NFV management, orchestration, and resource allocation system--a paradigm shift for the management of virtualized networks--and it requires minor changes to the current NFV architecture. We prove that our approach is feasible, as it has been implemented by extending the OpenMANO framework and validated on several network scenarios. Furthermore, we prove with performance tests that policy refinement scales well enough to support current and future virtualized networks.

The rapid evolution of network infrastructure through the softwarization of network elements has led to an exponential increase in the attack surface, thereby increasing the complexity of threat protection. In light of this pressing concern, European Telecommunications Standards Institute (ETSI) TeraFlowSDN (TFS), an open-source microservice-based cloud-native Software-Defined Networking (SDN) controller, integrates robust Machine-Learning components to safeguard its network and infrastructure against potential malicious actors. This work presents a comprehensive study of the integration of these Machine-Learning components in a distributed scenario to provide secure end-to-end protection against cyber threats occurring at the packet level of the telecom operator’s Virtual Private Network (VPN) services configured with that feature. To illustrate the effectiveness of this integration, a real-world emerging attack vector (the cryptomining malware attack) is used as a demonstration. Furthermore, to address the pressing challenge of energy consumption in the telecom industry, we harness the full potential of state-of-the-art Green Artificial Intelligence techniques to optimize the size and complexity of Machine-Learning models in order to reduce their energy usage while maintaining their ability to accurately detect potential cyber threats. Additionally, to enhance the integrity and security of TeraFlowSDN’s cybersecurity components, Machine-Learning models are safeguarded from sophisticated adversarial attacks that attempt to deceive them by subtly perturbing input data. To accomplish this goal, Machine-Learning models are retrained with high-quality adversarial examples generated using a Generative Adversarial Network.

Quantum key distribution (QKD) is a physical technology that enables the secure generation of bit streams (keys) in two separated locations. This technology is designed to provide a solution for very secure (quantum-safe) key agreement, which is nowadays at risk due to advances in quantum computing. The recent demonstration of a QKD network in the metropolitan area of Madrid shows how these networks can be deployed in current production infrastructure by following existing networking paradigms, such as software-defined networking. In particular, a three-node QKD network is implemented on the metropolitan area network using existing infrastructure and coexisting with other data and control services. On the other hand, telecommunication networks are drastically changing the way services are architectured. Users of the operator’s infrastructure are moving from traditional connectivity services (e.g., virtual private networks) to a set of interconnected network functions, either physical or virtual, in the shape of service function chaining (SFC). However, SFC users do not have a method to validate that the traffic flow is appropriately forwarded across the nodes in the network, a situation that may lead to very critical security breaches (e.g., a security node or a firewall in the chain that is bypassed). This work presents a method for validating ordered proof-of-transit (OPoT) on top of the Madrid Quantum Network. We first provide a general description of the QKD network deployed in Madrid. Then, we describe an existing security protocol for PoT in packet networks, analyzing its issues and vulnerabilities. Finally, this work presents a protocol for alleviating the security breach found in this work and for providing OPoT in SFC. Finally, an example of the real implementation is shown, where nodes being part of the OPoT scheme are provisioned with QKD-derived keys.