This paper examines how residual hardware impairments (RHI) influence the reliability of physical-layer authentication (PLA) in wireless systems enhanced by Reconfigurable Intelligent Surfaces (RIS). The study considers a scenario where a legitimate user and an attacker communicate with a receiver… Read More »Impact of Residual Hardware Impairments on RIS-aided Authentication
This paper presents a security framework designed for the emerging Cloud Continuum, where cloud, edge, and extreme-edge environments operate together to support next-generation 6G services. As networks become more distributed and dynamic, traditional static security mechanisms struggle to keep pace.… Read More »Securing Networks of the Future: A Programmable Security Monitoring Platform for Cloud Continuum
This paper presents an improved framework for physical-layer authentication (PLA) in multiuser wireless environments, where channel variations, measurement noise, and interference can make it difficult to reliably distinguish legitimate users from attackers. Traditional CSI-based authentication methods often suffer in such… Read More »Enhanced Multiuser CSI-Based Physical Layer Authentication Based on Information Reconciliation
This survey examines how Explainable AI (XAI) can strengthen security in 5G and future 6G networks, where AI models increasingly drive tasks such as intrusion detection, traffic classification, PHY-layer authentication, and anomaly detection. While these models offer strong performance, their… Read More »A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions
This paper presents a generalized multi-layer Intrusion Detection System (IDS) aimed at improving the security of modern smart buildings, where a mix of IoT devices, sensors, and network services creates a wide attack surface. To handle the high heterogeneity of… Read More »A Generalized Multi-Layer IDS for Smart Buildings
This paper presents a machine learning–driven localization framework that leverages Angle of Arrival (AoA) as a robust feature extracted from massive MIMO OFDM channel state information (CSI). The goal is to enable accurate user or device localization in complex outdoor… Read More »High-accuracy AoA-based Localization using Hierarchical ML Classifiers in Outdoor Environments
This paper investigates whether Angle of Arrival (AoA) can serve as a reliable feature for physical-layer authentication (PLA), particularly when an adversary attempts to impersonate a legitimate transmitter. While previous PLA methods often rely on features such as channel frequency… Read More »Leveraging Angle of Arrival Estimation against Impersonation Attacks in Physical Layer Authentication
This paper introduces DRACO, a decentralized and asynchronous federated learning framework tailored for wireless networks where communication delays, node heterogeneity, and topology variations make traditional synchronous FL inefficient. Unlike centralized approaches, DRACO removes the need for a server and allows… Read More »DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks
This paper introduces S-VOTE, a similarity-based voting mechanism designed to improve both efficiency and model performance in Decentralized Federated Learning (DFL). Unlike traditional federated learning, DFL operates without a central server, relying on peer-to-peer communication. While this avoids bottlenecks and… Read More »S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning
This paper presents HyperDtct, a hypervisor-based framework for detecting ransomware by monitoring system call behavior from outside the guest operating system. Rather than relying on in-guest agents or signature-based methods, both of which can be evaded by modern ransomware, HyperDtct… Read More »HyperDtct: Hypervisor-Based Ransomware Detection using System Calls