Driven by privacy concerns and the visions of Deep Learning, the last four years have witnessed a paradigm shift in the applicability mechanism of Machine Learning (ML). An emerging model, called Federated Learning (FL), is rising above both centralized systems and on-site analysis, to be a new fashioned design for ML implementation. It is a privacy preserving decentralized approach, which keeps raw data on devices and involves local ML training while eliminating data communication overhead. A federation of the learned and shared models is then performed on a central server to aggregate and share the built knowledge among participants. This paper starts by examining and comparing different ML-based deployment architectures, followed by in-depth and in-breadth investigation on FL. Compared to the existing reviews in the field, we provide in this survey a new classification of FL topics and research fields based on thorough analysis of the main technical challenges and current related work. In this context, we elaborate comprehensive taxonomies covering various challenging aspects, contributions and trends in the literature including core system models and designs, application areas, privacy and security and resource management. Further, we discuss important challenges and open research directions towards more robust FL systems.

As an alternative to centralized systems, which may prevent data to be stored in a central repository due to its privacy and/or abundance, Federated Learning (FL) is nowadays a game changer addressing both privacy and cooperative learning. It succeeds in keeping training data on the devices, while sharing locally computed then globally aggregated models throughout several communication rounds. The selection of clients participating in FL process is currently at complete/quasi randomness. However, the heterogeneity of the client devices within Internet of Things environment and their limited communication and computation resources might fail to complete the training task, which may lead to many discarded learning rounds affecting the model accuracy. In this paper, we propose FedMCCS, a multi-criteria based approach for client selection in FL. All of the CPU, Memory, Energy, and Time are considered for the clients resources to predict whether they are able to perform the FL task. Particularly, in each round, the number of clients in FedMCCS is maximized to the utmost, while considering each client resources and its capability to successfully train and send the needed updates. The conducted experiments show that FedMCCS outperforms the other approaches by (1) reducing the number of communication rounds to reach the intended accuracy, (2) maximizing the number of clients, (3) handling the least number of discarded rounds, and (4) optimizing the network traffic.

Internet of Vehicles and Vehicular networks have been compelling targets for malicious security attacks where several intrusion detection solutions have been proposed for protecting them. Nonetheless, their main problem lies in their heavy computation, which makes them unsuitable for next-generation AI-powered self-driving vehicles whose computational power needs to be primarily reserved for real-time driving decisions. To address this challenge, several approaches have been lately presented to take advantage of the cloud computing for offloading intrusion detection tasks to central cloud servers, thus reducing storage and processing costs on vehicles. However, centralized cloud computing entails high latency on intrusion detection related data transmission and plays against its adoption in delay-critical intelligent applications. In this context, this paper proposes a Vehicular Edge Computing (VEC) fog-enabled scheme allowing offloading intrusion detection tasks to federated vehicle nodes located within nearby formed ad-hoc vehicular fog to be cooperatively executed with minimal latency. The problem has been formulated as multi-objective optimization model and solved using a genetic algorithm maximizing offloading survivability in the presence of high mobility and minimizing computation execution time and energy consumption. Experiments performed on resource-constrained devices within actual ad-hoc fog environment illustrate that our solution significantly reduces the execution time of the detection process while maximizing the offloading survivability under different real-life scenarios.

While the usage of smart devices is increasing, security attacks and malware affecting such terminals are briskly evolving as well. Mobile security suites exist to defend devices against malware and other intrusions. However, they require extensive resources not continuously available on mobile terminals, hence affecting their relevance, efficiency and sustainability. In this paper, we address the aforementioned problem while taking into account the devices limited resources such as energy and CPU usage as well as the mobile connectivity and latency. In this context, we propose an ad-hoc mobile edge cloud that takes advantage of Wi-Fi Direct as means of achieving connectivity, sharing resources, and integrating security services among nearby mobile devices. The proposed scheme embeds a multi-objective resource-aware optimization model and genetic-based solution that provide smart offloading decision based on dynamic profiling of contextual and statistical data from the ad-hoc mobile edge cloud devices. The carried experiments illustrate the relevance and efficiency of exchanging security services while maintaining their sustainability with or without the availability of Internet connection. Moreover, the results provide optimal offloading decision and distribution of security services while significantly reducing energy consumption, execution time, and number of selected computational nodes without sacrificing security.

Multi-persona mobile computing has begun to make its way to determine the battle about practical strategy for adopting personal devices in workplace. Though its competency, multi-persona performance and viability are critically threatened by the limited resources of mobile devices. In recent years, mobile edge computing (MEC) has risen as promising paradigm within the internet of things era bringing benefits to the proximity of mobile terminals, leveraging intelligent computations offloading services to address the severity of their resource scarcity. Yet, embracing mobile edge-based services to augment personas resources and performance raises new concerns including determining what computations to offload for serving the highest number of mobile devices and reducing the remote execution fees imposed on the institution. In this context, we propose new cost-effective MEC-based solution to address these issues. We develop two-level multi-objective optimization realized through an intelligent offloading decision model able to settle both concerns, by minimizing processing, memory and energy while augmenting virtual mobile instances performance on a wide range of physical devices with minimal offloading service fees. We also propose a redesigned smart genetic-based method able to accelerate and reduce the overhead of offloading decision evaluation. Extensive analysis is performed and the results show that our proposition can get more quickly the offloading strategy than other schemes. The results also demonstrate the ability to enforce the virtual mobile devices by reducing local processing, memory usage, energy consumption and execution time along with acceptable minimal additional fees compared to other techniques.