News and Announcements

  • Keynote at IEEE WResNet6G 2025

    March 24, 2025

    Falko Dressler gave a keynote titled Cross-Technology Communication and Network Coding: A Great Team for Resilient Communication at IEEE WCNC International Workshop on Resilient 6G Networks (WResNet6G 2025), which was held in Milan, Italy.
    (link to more information)

  • Isabel von Stebut winning GI/ITG KuVS Best Bachelor Thesis Award

    March 18, 2025

    We congratulate Isabel von Stebut for winning the Best Bachelor Thesis Award of the GI/ITG Communication and Distributed Systems (KuVS) special interest group! The prize will be awarded at NetSys 2025. Isabel's thesis has already lead to a publications at IEEE PIMRC 2024 (ResCTC: Resilience in Wireless Networks through Cross-Technology Communication).

  • Lisa Y. Debus winning GI/ITG KuVS Best Master Thesis Award

    March 18, 2025

    We congratulate Lisa Y. Debus for winning the Best Master Thesis Award of the GI/ITG Communication and Distributed Systems (KuVS) special interest group! The prize will be awarded at NetSys 2025. Lisa's thesis has already lead to two publications at IEEE GLOBECOM 2023 (Reinforcement Learning-based Receiver for Molecular Communication with Mobility) and a follow-up journal paper published in IEEE Trans. on Molecular, Biological and Multi-Scale Communication (Synchronized Relaying in Molecular Communication: An AI-based Approach using a Mobile Testbed Setup).

  • Poster Presentation at AAAI

    February 25, 2025

    Our group member Osman Tugay Basaran presented our poster XAInomaly: Explainable, Interpretable, and Trustworthy Next Generation Ultra-reliable Low-latency Communications (xURLLC) in 6G Networks at the 39th Annual AAAI Conference on Artificial Intelligence at Pennsylvania Convention Center in Philadelphia, PA, USA. In this work, considering reliability and low-latency, real-time communications requirements of next generation wireless communication systems, to ensure that the AI/ML algorithms used in 6G and beyond networks are trustable and reliable, we proposed a XAInomaly framework that use our novel fastSHAP-C method which handle real-time XAI layer operations.
    (link to more information)

  • Paper Presentation at IEEE ICNC 2025

    February 19, 2025

    Christos Laskos presented our paper, Wi-Fi Ranging under Interference at the IEEE International Conference on Computing, Networking and Communications (ICNC 2025) in Honolulu, HI. In this paper, we demonstrate that time of arrival (ToA)-based ranging, utilizing the MUSIC super-resolution algorithm, is severely impacted by cross-technology and co-channel interference. This is due to the fact that the channel state information (CSI) obtained in the presence of interference includes not only the characteristics of the channel but also the interference itself. This corrupted CSI leads to persistent ToA errors.
    (link to more information)

  • New Elsevier High-Confidence Computing article

    February 19, 2025

    Our article Task Migration with Deadlines using Machine Learning-based Dwell Time Prediction in Vehicular Micro Clouds has been accepted for publication in Elsevier High-Confidence Computing. Edge computing is becoming ever more relevant to offload compute-heavy tasks in vehicular networks. In this context, the concept of vehicular micro clouds (VMCs) has been proposed to use compute and storage resources on nearby vehicles to complete computational tasks. As many tasks in this application domain are time critical, offloading to the cloud is prohibitive. Additionally, task deadlines have to be dealt with. This paper addresses two main challenges. First, we present a task migration algorithm supporting deadlines in vehicular edge computing. The algorithm is following the earliest deadline first model but in presence of dynamic processing resources, i.e., vehicles joining and leaving a VMC. This task offloading is very sensitive to the mobility of vehicles in a VMC, i.e., the so-called dwell time a vehicles spends in the VMC. Thus, secondly, we propose a machine learning-based solution for dwell time prediction. Our dwell time prediction model uses a random forest approach to estimate how long a vehicle will stay in a VMC. Our proposed approach is able to realize low-delay and low-failure task migration in dynamic vehicular conditions, advancing the state of the art in vehicular edge computing.
    (link to more information)

  • New IEEE/ACM Transactions on Networking article

    February 18, 2025

    Our article Jamming-Resilient Physical-to-Virtual Communications in Digital Twin Edge Networks has been accepted for publication in IEEE/ACM Transactions on Networking. As an integration of digital twin and edge computing, the digital twin edge networks (DITENs) have been proposed in recent years to fill the gap between physical edge networks and digital systems. Meanwhile, the multi-access wireless environments in edge computing make it hard to provide ultra-reliable and low-latency communications for digital twin, especially when the jamming attacks can be launched by the adversaries. This paper studies the jamming-resilient physical-to-virtual communication (PTVC) problem in DITENs despite strong cooperative jamming. Note that the previous jamming models mainly focus on the jamming behaviors from an individual adversary and are restricted by the energy budget limitation and uniform jamming assumption. In this paper, we consider a more comprehensive jamming model, in which f adversaries can cooperatively launch their jamming attacks in totally kwireless channels with unlimited power budget and non-uniform jamming signals. Both of the theoretical results and empirical simulations are conducted to show the resilience of our algorithms despite such a strong cooperative jamming model.
    (link to more information)

  • New Elsevier Computer Networks article

    February 16, 2025

    Our article XAInomaly: Explainable and Interpretable Deep Contractive Autoencoder for O-RAN has been accepted for publication in Elsevier Computer Networks. Generative Artificial Intelligence (AI) techniques have become integral part in advancing next generation wireless communication systems by enabling sophisticated data modeling and feature extraction for enhanced network performance. In the realm of open radio access networks (O-RAN), characterized by their disaggregated architecture and heterogeneous components from multiple vendors, the deployment of generative models offers significant advantages for network management such as traffic analysis, traffic forecasting and anomaly detection. In this study, we introduce the XAInomaly framework, an explainable and interpretable Semi-supervised (SS) Deep Contractive Autoencoder (DeepCAE) design for anomaly detection in O-RAN. Our approach leverages the generative modeling capabilities of our SS-DeepCAE model to learn compressed, robust representations of normal network behavior, which captures essential features, enabling the identification of deviations indicative of anomalies. To address the black-box nature of deep learning models, we propose reactive Explainable AI (XAI) technique called fastshap-C, which is providing transparency into the model's decision-making process and highlighting the features contributing to anomaly detection.
    (link to more information)

  • New International Journal of Microwave and Wireless Technologies article

    February 10, 2025

    Our article Fast Identification and Clustering of Multi-Path Components for Multi-band Industrial Wireless Channels has been accepted for publication in International Journal of Microwave and Wireless Technologies. Multi-path components are both the challenge and the resources to exploit in high-frequency wireless communication, especially in environment with complex reflections. To this end, identifying and clustering multi-path components is the foundation in tackling the challenges and boosting the utilization with reliable and correct information. Past research focuses either on extracting the path information, or on clustering the extracted components. In this paper, we propose a complete work flow that performs identification as well as clustering of multi-path components. We extend our previous work in clustering algorithm to indoor propagation measurements of three different frequency bands, as well as multiple transmitter-receiver locations. The ease of application highlights the wide-applying potential of high-frequency communication.
    (link to more information)

  • New staff member: Ahmed Hasan Ansari

    February 10, 2025

    We welcome Ahmed Hasan Ansari who joined our group in February 2025.

Load all older news

Last modified: 2024-04-28