This paper proposes a lightweight defense mechanism to protect AI models exposed through AI-as-a-Service (AIaaS) from black-box adversarial attacks. As future networks rely more on remotely accessed AI functions, models become vulnerable to malicious queries that subtly manipulate inputs and… Read More »A Novel Method to Mitigate Adversarial Attacks Against AI-as-a-Service Functionality
This paper presents SHERPA, an explainability-driven defense framework designed to protect Federated Learning (FL) systems from data poisoning attacks. FL allows distributed devices to collaboratively train a global model without sharing raw data, but this also opens the door for… Read More »SHERPA: Explainable Robust Algorithms for Privacy-Preserved Federated Learning in Future Networks to Defend Against Data Poisoning Attacks
This paper provides a concise overview of how security must evolve as we move toward 6G smart networks, where communication, sensing, and computing become tightly integrated. It highlights that future systems will rely heavily on distributed AI/ML, making the protection… Read More »Advancing Security for 6G Smart Networks and Services
This paper introduces ROBUST-6G, a European research initiative aimed at designing a comprehensive security platform for future 6G networks. As 6G moves toward deeply integrated digital: physical systems, the project focuses on building security mechanisms that are data-driven, automated, trustworthy,… Read More »ROBUST-6G: Smart, Automated, and Reliable Security Service Platform for 6G
As wireless systems evolve toward 6G, AI becomes increasingly central to how networks operate, optimize themselves, and deliver advanced services. But with greater autonomy and complexity comes a critical requirement: the decisions made by AI models must be understandable, transparent,… Read More »Explainable AI for 6G Use Cases: Technical Aspects and Research Challenges
This paper introduces a new perspective on securing wireless status-update systems by combining physical-layer security with the concept of information freshness. Instead of relying on traditional secrecy metrics such as secrecy capacity or outage probability, the authors focus on Age… Read More »Secure Status Updates under Eavesdropping: Age of Information-based Secrecy Metrics
Federated Learning (FL) relies on many distributed clients training a shared global model without sending raw data to the server. However, one of the core challenges in FL is determining which clients should participate in each training round, especially when… Read More »Version Age-Based Client Scheduling Policy for Federated Learning
Monitoring large IoT networks is challenging, especially when devices operate in remote environments and faults cannot be easily observed. This paper introduces a semantics-aware active fault detection approach, where a monitor intelligently decides when to probe a remote sensor to… Read More »Semantics-Aware Active Fault Detection in Status Updating Systems
As large language models continue to grow, running them efficiently on small edge devices remains one of AI’s biggest challenges. This paper explores how LLM inference can be decentralized across a network of energy-harvesting devices each powered by intermittent renewable… Read More »Decentralized LLM Inference over Edge Networks with Energy Harvesting
This paper proposes a new method for estimating the reliability of machine learning predictions applied to Earth observation (EO) and health-related datasets, with a focus on forecasting mosquito abundance (MA). The authors develop a Variational Autoencoder (VAE)-based confidence metric that… Read More »A Latent Space Metric for Enhancing Prediction Confidence in Earth Observation Data