As Federated Learning (FL) expands to larger and more distributed environments, consistency in training is challenged by network-induced delays, clock unsynchronicity, and variability in client updates. This combination of factors may contribute to misaligned contributions that undermine model reliability and convergence. Existing methods like staleness-aware aggregation and model versioning address lagging updates heuristically, yet lack mechanisms to quantify staleness, especially in latency-sensitive and cross-regional deployments. In light of these considerations, we introduce SyncFed, a time-aware FL framework that employs explicit synchronization and times-tamping to establish a common temporal reference across the system. Staleness is quantified numerically based on exchanged timestamps under the Network Time Protocol (NTP), enabling the server to reason about the relative freshness of client updates and apply temporally informed weighting during aggregation. Our empirical evaluation on a geographically distributed testbed shows that, under SyncFed, the global model evolves within a stable temporal context, resulting in improved accuracy and information freshness compared to round-based baselines devoid of temporal semantics.

The rapid innovation in the automotive industry highlights the increasing importance of user comfort, especially when integrated with advanced learning scenarios. However, there is a noticeable gap in research focusing on vehicle cabin comfort, particularly in the context of learning and personalization of features. This study conducts a systematic literature review to assess the current state of research in this area. By utilizing federated learning with personalization, a novel and promising technique, various use cases related to vehicle interior comfort are explored. These use cases help derive the requirements needed to address the research question. The methodology of the systematic literature review is detailed, including the evaluation of specific prerequisites. The key finding reveals that no existing study meets all the predefined requirements, underscoring the need for further research in this domain.

Most of the existing vehicle comfort features operate solely based on user input, lacking consideration for individual preferences, and environmental conditions. This manual adjustment while driving can lead to potential distractions, and jeopardizing user safety. On the other hand, implementing a system where the vehicle control unit learns individual preferences and autonomously adjusts accordingly would significantly enhance the driving experience. In this paper, we examine the thermal comfort of users as one of the comfort features within software-defined vehicles. Given that thermal comfort is influenced by both physiological and external factors, and people have diverse individual preferences, this paper proposes leveraging personalized federated learning to automate and personalize temperature regulation, thereby enhancing thermal comfort of passengers in the vehicle cabin. To validate this concept, we conducted experiments employing a prototype equipped with sensors to collect real-time data, which is then used to train a predictive model. The model's accuracy was assessed using metrics and compared against a centralized approach. In addition, we used a simulator to visualize the potential improvement in thermal comfort with the predicted values. Our findings indicate that temperature control in the vehicle cabin, utilizing federated learning for individualized regulation, outperforms conventional learning approaches, thus yielding significant improvement for thermal comfort of passengers.

Cyberattacks are increasingly threatening net-worked systems, often with the emergence of new types of unknown (zero-day) attacks and the rise of vulnerable devices. uch attacks can also target multiple components of a Supply Chain, which can be protected via Machine Learning (ML)-based Intrusion Detection Systems (IDSs). However, the need to learn large amounts of labelled data often limits the applicability of ML-based IDSs to cybersystems that only have access to private local data, while distributed systems such as Supply Chains have multiple components, each of which must preserve its private data while being targeted by the same attack To address this issue, this paper proposes a novel Decentralized and Online Federated Learning Intrusion Detection (DOF-ID) architecture based on the G-Network model with collaborative learning, that allows each IDS used by a specific component to learn from the experience gained in other components, in addition to its own local data, without violating the data privacy of other components. The performance evaluation results using public Kitsune and Bot-loT datasets show that DOF -ID significantly improves the intrusion detection performance in all of the collaborating components, with acceptable computation time for online learning.