Farag Sallabi

Asadullah Tariq, Tariq Qayyum, Mohamed Adel Serhani et al.

Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressing data privacy and computational concerns. However, FL faces a major bottleneck due to high communication overhead from frequent model updates between devices and the server, limiting deployment in resource-constrained wireless networks. In this paper, we propose a three-fold strategy. Firstly, an Adaptive Feature-Elimination Strategy to drop less important features while retaining high-value ones; secondly, Adaptive Gradient Innovation and Error Sensitivity-Based Quantization, which dynamically adjusts the quantization level for innovative gradient compression; and thirdly, Communication Frequency Optimization to enhance communication efficiency. We evaluated our proposed model's performance through extensive experiments, assessing accuracy, loss, and convergence compared to baseline techniques. The results show that our model achieves high communication efficiency in the framework while maintaining accuracy.

Asadullah Tariq, Mohamed Adel Serhani, Farag Sallabi et al.

Federated Learning (FL) has emerged as a significant advancement in the field of Artificial Intelligence (AI), enabling collaborative model training across distributed devices while maintaining data privacy. As the importance of FL increases, addressing trustworthiness issues in its various aspects becomes crucial. In this survey, we provide an extensive overview of the current state of Trustworthy FL, exploring existing solutions and well-defined pillars relevant to Trustworthy . Despite the growth in literature on trustworthy centralized Machine Learning (ML)/Deep Learning (DL), further efforts are necessary to identify trustworthiness pillars and evaluation metrics specific to FL models, as well as to develop solutions for computing trustworthiness levels. We propose a taxonomy that encompasses three main pillars: Interpretability, Fairness, and Security & Privacy. Each pillar represents a dimension of trust, further broken down into different notions. Our survey covers trustworthiness challenges at every level in FL settings. We present a comprehensive architecture of Trustworthy FL, addressing the fundamental principles underlying the concept, and offer an in-depth analysis of trust assessment mechanisms. In conclusion, we identify key research challenges related to every aspect of Trustworthy FL and suggest future research directions. This comprehensive survey serves as a valuable resource for researchers and practitioners working on the development and implementation of Trustworthy FL systems, contributing to a more secure and reliable AI landscape.

Ting-Yu Mu, Ala Al-Fuqaha, Khaled Shuaib et al.

Modern information technology services largely depend on cloud infrastructures to provide their services. These cloud infrastructures are built on top of datacenter networks (DCNs) constructed with high-speed links, fast switching gear, and redundancy to offer better flexibility and resiliency. In this environment, network traffic includes long-lived (elephant) and short-lived (mice) flows with partitioned and aggregated traffic patterns. Although SDN-based approaches can efficiently allocate networking resources for such flows, the overhead due to network reconfiguration can be significant. With limited capacity of Ternary Content-Addressable Memory (TCAM) deployed in an OpenFlow enabled switch, it is crucial to determine which forwarding rules should remain in the flow table, and which rules should be processed by the SDN controller in case of a table-miss on the SDN switch. This is needed in order to obtain the flow entries that satisfy the goal of reducing the long-term control plane overhead introduced between the controller and the switches. To achieve this goal, we propose a machine learning technique that utilizes two variations of reinforcement learning (RL) algorithms-the first of which is traditional reinforcement learning algorithm based while the other is deep reinforcement learning based. Emulation results using the RL algorithm show around 60% improvement in reducing the long-term control plane overhead, and around 14% improvement in the table-hit ratio compared to the Multiple Bloom Filters (MBF) method given a fixed size flow table of 4KB.

Mohammad A. Salahuddin, Ala Al-Fuqaha, Mohsen Guizani et al.

We propose an agile softwarized infrastructure for flexible, cost effective, secure and privacy preserving deployment of Internet of Things (IoT) for smart healthcare applications and services. It integrates state-of-the-art networking and virtualization techniques across IoT, fog and cloud domains, employing Blockchain, Tor and message brokers to provide security and privacy for patients and healthcare providers. We propose a novel platform using Machine-to-Machine (M2M) messaging and rule-based beacons for seamless data management and discuss the role of data and decision fusion in the cloud and the fog, respectively, for smart healthcare applications and services.