Future 6G networks should not only react after connections degrade, they should anticipate risk before service is interrupted. Have you ever been on an important video call or playing an online game while traveling, only for the connection to suddenly freeze or drop? As we move toward ultra-fast 6G wireless technology, keeping mobile applications running smoothly while users move across changing network zones remains a major challenge. One reason for these interruptions is that many current network decisions rely on a single estimate of future performance. When the network decides whether to keep a user connected to the current local server or move them to another one, that decision may be based on one predicted value. If this prediction is too optimistic, or if a short burst of interference occurs, the system may react too early, too late, or trigger unnecessary server changes. This can lead to avoidable signaling, degraded performance, or temporary service disruption. Researchers from Technische Universität Braunschweig propose a new risk-aware approach to this problem. Instead of relying only on a single prediction, the framework estimates a range of possible future network speeds and calculates a calibrated probability that the connection may fall below the required service level. This allows the network to make decisions with a clearer understanding of uncertainty. A simple way to think about it is a weather forecast. A basic forecast might say, “Tomorrow will be sunny.” A more useful forecast says, “The temperature will likely be between 20 and 24 degrees, with a 30% chance of rain.” In the same way, the proposed system does not only ask, “How fast will the connection be?” It also asks, “How confident are we, and how likely is a slowdown?” Using this information, the network’s optimizer can decide whether to keep the current connection, switch to a better local server, or avoid risky choices that may soon degrade. The goal is to maintain smooth service while avoiding unnecessary server switching. A key strength of the work is that it is designed to fit within existing 3GPP and ETSI MEC standards. The controller can run as an edge application and use existing mechanisms for network information, policy control, traffic steering, and application mobility. This makes the approach more practical for future deployment. The evaluation shows that the risk-aware controller achieves higher expected throughput than a controller based only on single-value predictions. It also gives network operators a tuning knob to balance speed and reliability. As 6G networks become more dynamic, this work shows that service continuity should not depend only on reacting after problems occur. By considering uncertainty and risk before making decisions, future networks can become more stable, adaptive, and reliable for users. Publication Details Conformal Prediction and Risk-Based Optimization of Service Continuity in 6G Edge Networks Authors: Zied Ennaceur, Admela Jukan MARE Partner: Technische Universität Braunschweig (TUBS) Publication: IEEE International Conference on Communications (ICC) , Glasgow, Scotland, UK, 24–28 May 2026. Conference website. Abstract: We study the problem of service continuity in 6G networks and propose a solution aligned with current mobile network standards that integrates conformal prediction and risk-aware throughput estimation to anticipate short-term degradations and, in addition, to optimize application and session continuity during network topology changes. Our pipeline combines throughput prediction over short horizons with calibration based on split conformal prediction to produce sharp intervals with coverage guarantees, and a throughput degradations estimator that provides the probability that throughput falls below the SLA threshold on each link. A risk-aware optimizer then selects associations that balance expected throughput, reliability, and continuity. Experiments on emulated mobile network traces demonstrate that the performance improves by incorporating uncertainty and calibrated risk estimation. Experiments on emulated mobile network traces demonstrate that the degradation risk model is well calibrated with a Brier score of 0.095, an Expected Calibration Error of 0.068, and a PR–AUC of 0.810, and that incorporating uncertainty and calibrated risk improves control decisions. The risk-aware controller consistently attains higher expected throughput than the commonly used point-estimate baseline at matched reassociation rates, and it can identify network operating regimes with low SLA degradation, e.g., 7.9% violations at 999 Mb expected throughput for ε = 0.40. DOI: https://doi.org/10.5281/zenodo.19095625 Access Publication

As our world becomes increasingly interconnected through 5G networks and the Internet of Things (IoT), the security of these systems has become ever more important. This study, published in Expert Systems with Applications, introduces a groundbreaking approach to protecting these networks while maintaining user privacy. The Motivation: Security vs. Privacy Traditional security systems, known as Intrusion Detection Systems (IDS), act like a digital burglar alarm, constantly scanning network traffic for signs of a hack or “intrusion”. Historically, to make these systems smart, researchers had to collect massive amounts of data from various devices and store them in a central location. Nowadays, this raises serious privacy issues and users hesitate to share their private data with a central server, even for security purposes. The Background: Where Standard Models Fail To solve the privacy problem, scientists previously turned to Federated Learning. In this setup, instead of sending raw data to a central server, each device (or “node”) trains its own security model locally and only shares the “lessons learned” (mathematical updates). While this protects privacy, it faces the major hurdle of “unbalanced data”. In a real-world 5G network, this refers to when some devices might rarely see an attack, while others are bombarded with attacks. Standard Federated Learning models struggle to learn effectively when the data is so unevenly distributed, often failing to recognize new or “unknown” types of cyberattacks. The New Frontier: Federated Transfer Learning The researchers behind this new study have introduced Federated Transfer Learning to 5G network security. The “Transfer” part is the key innovation – which introduces a “pre-training” phase that significantly boosts the intelligence of local security models. To understand this in a professional context, imagine a global medical research network. A prestigious teaching hospital uses a massive, diverse database of millions of patient records to develop a highly sophisticated diagnostic tool (this is the “Source Domain”). This tool is then shared with small, private clinics (the “Target Domain”). Even if a small clinic has never encountered a rare disease before, the tool “transfers” the foundational knowledge from the large hospital, allowing the local clinic to identify the illness immediately while keeping its own patients’ records strictly private. In the context of 5G, the system is first trained on a massive, well-documented set of cyberattacks. It then “transfers” this foundational knowledge to individual nodes in a 5G network. This allows even the most isolated devices – those that haven’t seen many attacks, to benefit from a global pool of expertise. Why this is a Game-Changer The results of this study are impressive. The researchers found that for devices with very little exposure to malicious traffic, the new Federated Transfer Learning approach improved the detection of unknown attacks by over 62%. Specifically, detection rates jumped from a meager 19% under old methods to a robust 81.7%. Furthermore, the overall accuracy of the system remained high, reaching over 91% even in the most challenging, “imbalanced” scenarios where traditional models frequently failed. By combining the privacy-preserving nature of Federated Learning with the intelligence-sharing power of Transfer Learning, this research paves the way for a 5G future that is faster and significantly more resilient against the evolving landscape of cyber threats. Publication Details Federated transfer learning-based intrusion detection system in 5G networks Authors: Andrea Bellmunt, Beatriz Otero, Eva Rodríguez, Xavier Masip-Bruin MARE Partner: Universitat Politècnica de Catalunya (UPC) Journal: Expert Systems with Applications, 5 April 2026, Article: 130868, Volume: Volume 305. Journal website. Abstract: The development of Intrusion Detection Systems (IDS) for the Internet of Things (IoT) and 5G networks is rapidly advancing. This study investigates the application of federated architectures to train detection models while preserving data privacy by eliminating the need for data sharing among devices. We propose a Federated Transfer Learning (FTL) model tailored for scenarios with unbalanced nodes, enhancing the detection capabilities for unknown attacks compared to conventional Federated Learning (FL) approaches. Utilizing the Bot-IoT dataset as the source domain and the UNSW-NB15 dataset as the target domain, our experiments reveal significant improvements in detection performance. Specifically, nodes characterized by lower proportions of malicious traffic demonstrate up to a 62.614 % enhancement in detecting unknown attacks, increasing detection rates from 19.090 % to 81.704 %. Moreover, our findings indicate that FTL not only improves the identification of unknown threats but also maintains robust performance in detecting both attacks and benign traffic. Notably, the minimum accuracy achieved by the most imbalanced node reaches 0.912, in contrast to 0.741 with standard FL models. These results highlight the potential of FTL to train robust models across distributed nodes while ensuring privacy, thereby contributing to improved security measures in IoT and 5G networks. DOI: https://doi.org/10.1016/j.eswa.2025.130868 Access Publication

MARE will be present at two key conferences in the coming weeks. These are: The 32nd International Conference on Telecommunications (ICT), which will be held 20-22 May 2026 in Thessaloniki, Greece The 2026 EuCNC & 6G Summit which will be held 2-5 June 2026 in Malaga, Spain Please read more of our presence below, and we hope to meet you there! MARE @ ICT 2026 MARE will be present at ICT 2026, presenting the project with a poster Thursday 21st May. Come along to the Conference Poster session and meet our expert who will be able to inform you on the MARE project! MARE @ EuCNC & 6G Summit 2026 MARE will be present at the EuCNC & 6G Summit with a booth! Featuring details of the MARE Programmable, Modular and Disaggregated Security Plane, demos from its Proof of Concepts, and experts at hand, you will be able to learn more complete details about the MARE project and its activities! We look forward to meeting you soon!

As wireless networks evolve toward 6G, ensuring reliability and security in challenging environments is more important than ever. Today’s networks are designed to resist disruptions such as interference or malicious attacks. But what if future networks could do something even smarter – improve their performance because of them? This is exactly the idea explored in a new MARE publication titled “A Cross-Layer Analysis of Network Antifragility with RIS-assisted Links under Jamming Attacks”. The paper introduces an innovative concept known as network antifragility, showing how next-generation networks can not only survive hostile conditions but actually benefit from them. From resilience to antifragility Traditionally, network resilience means maintaining service when things go wrong. Antifragility goes a step further. Inspired by the work of statistician and risk theorist Nassim Nicholas Taleb, who originally framed the term in the context of financial systems and risk management, antifragility describes systems that gain strength from disruption, rather than merely resisting it. Taleb coined the term in his book Antifragile: Things That Gain from Disorder, defining it as a property of systems that improve their performance with exposure to volatility, shocks, and stressors, going beyond both robustness and resilience. In this study, researchers apply this concept to wireless communications for the first time at a network level, demonstrating that under certain conditions, adversity (such as interference or jamming) can be turned into an advantage. The work focuses on Reconfigurable Intelligent Surfaces (RIS) – programmable surfaces that can reflect and shape wireless signals. RIS technology is expected to play a key role in 6G by extending coverage, improving efficiency, and enabling smarter control of the radio environment. When jamming helps instead of hurts Wireless jamming attacks are usually seen as a serious threat, as they inject unwanted signals to disrupt communication. In this research, however, the team shows that, under certain conditions, jamming signals can be reused as an additional resource. By carefully detecting, classifying, and adapting to different types of interference, RIS-assisted networks can transform harmful signals into constructive ones. In some scenarios, the network’s data throughput increased by up to five times compared to normal, jammer-free operation. This is a striking example of antifragile behavior. Smarter networks across all layers What makes this work particularly relevant for MARE is its cross-layer approach. Instead of focusing only on the physical signal level, the study connects low-level signal behavior with higher-level network decisions, such as routing and link selection. This means future networks could automatically favor communication paths that perform better because of interference, leading to self-optimizing, adaptive, and more trustworthy 6G systems. Why this matters for MARE and beyond​ This publication highlights how MARE is helping redefine network security for the 6G era. Rather than treating uncertainty and attacks purely as risks, the project explores how variability can be harnessed intelligently. The findings open up a new design philosophy for future networks – one where disruption is not just mitigated but strategically exploited to improve performance, resilience, and efficiency. As 6G research accelerates, this work positions MARE at the forefront of building networks that don’t just withstand challenges – they grow stronger because of them. Publication Details A Cross-Layer Analysis of Network Antifragility with RIS-assisted Links under Jamming Attacks Authors: M. Bensalem, T. Röthig, and A. Jukan. MARE Partner: Technische Universität Braunschweig (TUBS) Journal: IEEE Networking Letters, November 2025. Journal website. Abstract: Antifragility is an economics term defined as measure of (monetary) benefits gained from the adverse events and variability of the markets. This paper integrates for the first time the antifragility into the network based on communication links with Reconfigurable Intelligent Surface (RIS) affected by a jamming attack. We analyze whether antifragility can be achieved for several jamming models. Beyond the link-level gains, the results reveal how antifragile RIS-assisted links can be integrated into multi-hop systems to improve end-to-end network resilience, connectivity, and throughput under adversarial effects. DOI: https://doi.org/10.1109/LNET.2025.3635777 Access Publication

The journey toward 6G is not just about faster speeds or greater connectivity. It’s about creating smarter, self-optimizing networks that can think, learn and adapt in real time. One of the most exciting innovations making this possible, is the concept of the Network Digital Twin (NDT) – a virtual mirror of a physical network that allows researchers to model, test and improve its performance safely and intelligently. A new paper by the NCSR Demokritos team, developed under the MARE project, presents a major step forwards in this area. Titled “Design and Evaluation of a Network Digital Twin Framework for 5G/6G Architectures”, the publication demonstrates how digital twin technology can help design and manage intelligent, AI-driven networks that will be the foundation of the 6G era. Network Digital Twin framework for native-AI support in a 6G system What is a network Digital Twin? Imagine having a complete digital replica of a network – one that updates in real time, mimicking how data flows, how devices connect and how services behave. This digital twin allows engineers to experiment safely with new technologies, predict problems before they happen and test solutions without disrupting real-world services. For example, an operator could use a digital twin to simulate a surge in user demand or a cyber-attack and immediately see how the network would react. The lessons learned can then be applied to strengthen the actual deployed network. Bridging the physical and the virtual The paper presents how the research team designed and implemented a full Network Digital Twin framework, integrating it with a real 5G testbed. Using open-source tools such as Open5GS, Prometheus and Grafana, the team created a virtual environment that accurately reflects real network conditions. This environment was used to compare the performance of the digital twin with the physical network under identical scenarios – such as different user loads or varying quality-of-service requirements. The results showed that the digital twin could reproduce real-world behavior, confirming its value as a safe and reliable testing ground. Network Digital Twin framework for native-AI support in a 6G system AI/ML framework for native-AI support in a 6G system Why this matters for 6G and MARE In the 6G vision, AI will play a central role in managing complex networks. However, AI models need vast amounts of accurate data to learn effectively – and collecting that data directly from live networks is often too costly or risky. That’s where digital twins come in. They can generate realistic data and simulate network conditions, enabling AI systems to be trained and optimized before being deployed in the real world. This is particularly important for security, resilience and efficiency purposes. These are also three pillars of the MARE project’s mission to create trustworthy 6G ecosystems. A foundation for the Future This work marks a milestone in building the foundations of AI-driven, self-aware networks. The Network Digital Twin framework developed by NCSR Demokritos demonstrates how European research is leading the way in designing secure and intelligent 6G systems. By merging physical and virtual worlds, MARE and its partners are shaping a future where our networks don’t just connect us – they also learn, adapt and protect us too. Publication Details Design and Evaluation of a Network Digital Twin Framework for 5G/6G Architectures Authors: I. Vasalos, M. Christopoulou, A. Vasalos, M. A. Kourtis, N. Dimitriou and G. Xylouris. MARE Partner: National Centre For Scientific Research Demokritos (NCSRD) Publication: 2025 21st International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), Lucca, Italy, 2025, pp. 915-920. Conference website. Abstract: Network Digital Twin (NDT) systems serve as a real-time, virtualized replica of physical networks, enabling closed-loop automation and AI/ML driven network intelligence. In this paper, we present a comprehensive approach to implementing an NDT framework tailored for B5G/6G networks. Through the proposed methodology, we demonstrate the generation of the NDT model, the accurate modeling of network topology, and the seamless synchronization with real world network operations. Our research delves into the deployment_and validation of an NDT prototype platform, seamlessly integrated with a 5G physical network testbed. We also present the end-to-end deployment of the framework and showcase its integration with a physical 5G testbed, effectively demonstrating its capability to support AI-native functionalities in next-generation mobile networks. DOI: https://doi.org/10.1109/DCOSS-IoT65416.2025.00139 Access Publication

On Friday 5th December 2025, the MARE 6G SNS project was presented by its technical Coordinator Professor Xavi Masip at the “Architecting Trust in 6G: Technical Insights from SNS-JU Projects” webinar. The event brought together several ongoing SNS projects to discuss emerging security and trust challenges in the path toward 6G. During his presentation, Professor Masip introduced MARE’s vision for a novel, software-driven security plane designed to deliver reliable security services across future 6G infrastructures. With the project approaching its first year, he explained how MARE is moving beyond traditional, attack-specific cybersecurity approaches, by creating an open, programmable and modular framework built from “Security Functions.” These Security Functions are composed dynamically from fundamental “DOTs”, which are security assets contributed by partners or external developers, and which can be orchestrated to detect, mitigate and even prevent security incidents. PDF DOWNLOAD A key innovation presented was MARE’s pre-assessment ecosystem, an evolution of concepts developed during the HORSE project. This environment uses simulation, emulation and real testbeds to analyse both the impact of attacks and the effectiveness of mitigation strategies before they are deployed. This proactive capability is essential, as 6G’s evolving architecture and continuous introduction of new technologies will expand the attack surface in unpredictable ways. Professor Masip also presented MARE’s thematic approach to defining 6G cybersecurity challenges, identifying five vulnerability areas and 11 representative attacks, each of which will be demonstrated through dedicated Proof-of-Concepts. This will help the project anticipate the dynamic 6G threat landscape and develop adaptable Security Functions suited for both reactive and proactive responses. Concluding his talk, Professor Masip emphasised that MARE’s software-based security plane, which will be open, interoperable and easily integrated to network architectures, can be deployed across any component of the emerging 6G architecture, supporting a more secure and trustworthy next-generation network ecosystem.

We are pleased to announce that Architecting Trust in 6G: Technical Insights from SNS JU Projects – an upcoming webinar, will feature the MARE project. The event will take place online on 5 December 2025, 10:00-13:00 CET and will gather leading initiatives working on 6G trust, security, and privacy. What to Expect The webinar will showcase technical enablers for trustworthy 6G networks, including: Security orchestration, Privacy-preserving architectures, Cyber threat intelligence, Trust evaluation, Security planes, Digital twins, ML-driven threat prediction, Confidential computing. Projects involved will present results, prototypes and validation activities that illustrate how 6G can be built with trust from the ground up. As part of this lineup, MARE will present its modular and adaptive security plane — offering insight into how our programmable security building blocks, orchestration engine, monitoring/abstraction layer and testing environments come together to face the challenges of 6G threats. Why you should Join You should join us in this webinar to: Learn about the latest technical advances in 6G security and trust from multiple SNS-JU projects, including MARE, See demos, prototypes and validation results — not just theory, but working solutions, Understand how cross-project collaboration is shaping the standards and infrastructure for future 6G networks, Join a network of researchers, operators and innovators committed to secure, resilient and trustworthy 6G. Webinar Details & Registration Date & Time: 5 December 2025 | 10:00–13:00 CET Format: Fully online Full Webinar Details Register for Webinar