Nowadays, IoT networks and devices exist in our everyday life, capturing and carrying unlimited data. However, increasing penetration of connected systems and devices implies rising threats for cybersecurity with IoT systems suffering from network attacks. Artificial Intelligence (AI) and Machine Learning take advantage of huge volumes of IoT network logs to enhance their cybersecurity in IoT. However, these data are often desired to remain private. Federated Learning (FL) provides a potential solution which enables collaborative training of attack detection model among a set of federated nodes, while preserving privacy as data remain local and are never disclosed or processed on central servers. While FL is resilient and resolves, up to a point, data governance and ownership issues, it does not guarantee security and privacy by design. Adversaries could interfere with the communication process, expose network vulnerabilities, and manipulate the training process, thus affecting the performance of the trained model. In this paper, we present a federated learning model which can successfully detect network attacks in IoT systems. Moreover, we evaluate its performance under various settings of differential privacy as a privacy preserving technique and configurations of the participating nodes. We prove that the proposed model protects the privacy without actually compromising performance. Our model realizes a limited performance impact of only ~ 7% less testing accuracy compared to the baseline while simultaneously guaranteeing security and applicability.

In recent years, Artificial Intelligence (AI) technology has seen significant growth due to advancements in machine learning (ML) and data processing, as well as the availability of large amounts of data. The integration of AI with eXtended Reality (XR) technologies such as Virtual Reality (VR) and Augmented Reality (AR) can create innovative solutions and provide intuitive interactions and immersive experiences across various sectors, including education, entertainment and healthcare. The presented paper describes the innovative Voice-drive interaction in XR spaces (VOXReality)* initiative, funded by the European commission, that integrates language and vision-based AI with unidirectional or bidirectional exchanges to drive AR and VR, allowing for natural human interactions with XR systems and creating multi-modal XR experiences. It aligns Natural Language Processing (NLP) and Computer Vision (CV) parallel progress to design novel models and techniques that integrate language and visual understanding with XR, providing a holistic understanding of goals, environment, and context. VOXReality plans to validate its visionary approaches through three use cases such as a XR personal assistant, real-time verbal communication in virtual conferences, and immersive experience for the audience of theatrical plays.* Funded by European Union (Grant agreement ID: 101070521)