The rise of the Internet of Things (IoT) has led to the integration of various devices into smart homes, significantly increasing the complexity and vulnerability of home networks. Consequent network performance issues often lead to complaints directed at Broadband Service Providers (BSPs), which may arise from either legitimate usage or malicious cyber attacks. BSPs, however, lack visibility into client-side networks, which is partly due to privacy concerns. This makes it hard to identify the true cause of performance problems. While previous research has tackled these challenges using Machine Learning (ML) techniques, few studies have approached the problem from the perspective of BSPs. They need a solution that is scalable, accurate, and privacy-preserving. Existing centralized ML models fail to generalize across these heterogeneous environments and provide low accuracy. We address this gap by introducing a novel Federated Learning (FL) framework for smart home device classification and attack detection. The proposed approach offers a privacy-preserving, scalable framework that can achieve accuracies of more than 80%. This framework can be installed inside the existing resource-constrained home gateways, making it suitable for large-scale deployment by BSPs.

Smart homes are increasingly vulnerable to cyberattacks that lead to network instability, causing homeowners to lodge complaints with their Broadband Service Providers (BSPs). Therefore, effective and timely detection of cyberattacks is crucial for both customers and BSPs. Address Resolution Protocol (ARP) spoofing is one of the most common attacks that can facilitate larger and more severe follow-up attacks. Unfortunately, there are currently no methods that can effectively detect and mitigate ARP spoofing in smart homes from a BSP’s perspective. Current Machine Learning (ML)-based methods often rely on a single dataset from a controlled lab environment designed to mimic a single home, assuming that the results will generalize to all smart homes. Our findings indicate that this assumption is flawed. They are also unsuitable for smart homes from a BSP’s perspective, as they require custom applications, introduce additional overhead, and often rely on the injection of probing traffic into the network. To address these issues, we developed an algorithm that can detect ARP spoofing in smart home networks, regardless of the network structure or connected devices. It uses a cross-protocol strategy by correlating ARP packets with Dynamic Host Configuration Protocol (DHCP) messages to validate address bindings. We evaluated our method using four public datasets and two real-world testbeds, achieving 100% detection accuracy in all scenarios. In addition, the algorithm requires only little computational overhead, confirming its suitability for use by BSPs to detect and mitigate ARP spoofing attacks in smart homes.

Until today, Physical Layer Security (PLS) has been a concept from information theory without practical implementations. We here describe a demonstration of how PLS can be achieved with common off-the-shelf WiFi equipment and open-source software. The key principle is that we make intelligent use of the architecture of a wireless network instead of trying to control every link individually on the physical layer.

Physical Layer Security (PLS) is widely recognized as a promising approach to secure wireless communications through the exploitation of the physical properties of the wireless channel. However, until today, PLS has mostly been a concept from information theory without practical implementations. In this paper, we present an actual implementation of PLS in a wireless network. We achieved this by leveraging the flexibility and control granularity offered by the relatively new concept of spectrum programming, by which we were able to control and degrade the quality of the eavesdropper’s channel by virtually manipulating the connectivity of the legitimate station. The key feature of our design is that we make intelligent use of the architecture of a wireless network instead of trying to control every link individually on the physical layer. The PLS implementation is built using off-the-shelf hardware and open-source software which makes it cost-effective and easy to replicate.

The broadcasting nature of the wireless medium makes exposure to eavesdroppers a potential threat. Physical Layer Security (PLS) has been widely recognized as a promising security measure complementary to encryption. It has recently been demonstrated that PLS can be implemented using off-the-shelf equipment by spectrum-programming enhanced Software-Defined Networking (SDN), where a network controller is able to execute intelligent access point (AP) selection algorithms such that PLS can be achieved and secrecy capacity optimized. In this paper we provide a basic system model for such implementations. We also introduce a novel secrecy capacity optimization algorithm, in which we combine intelligent AP selection with the addition of Friendly Jamming (FJ) by the not-selected AP.

Next generation mobile networks have proposed the integration of Unmanned Aerial Vehicles (UAVs) as aerial base stations (UAV-BS) to serve ground nodes. Despite the advantages of UAV-BSs, their dependence on the on-board, limited-capacity battery hinders their service continuity. Shorter trajectories can save flying energy, however UAV-BSs must also serve nodes based on their service priority since nodes' service requirements are not always the same. In this paper, we present an energy-efficient trajectory optimization for a UAV assisted IoT system in which the UAV-BS considers the IoT nodes' service priorities in making its movement decisions. We solve the trajectory optimization problem using Double Q- Learning algorithm. Simulation results reveal that the Q-Learning based optimized trajectory outperforms a benchmark algorithm, namely Greedily served algorithm, in terms of reducing the average energy consumption of the UAV-BS as well as the service delay for high priority nodes.

Next generation mobile networks have proposed the integration of Unmanned Aerial Vehicles (UAVs) as aerial base stations (UAV-BS) to serve ground nodes with potentially varying QoS requirements. However, the dependence on the on-board, limited-capacity battery of the UAV-BS limits their service continuity. While conserving energy is important, meeting the QoS requirements of the ground nodes is equally important. We present an energy-efficient trajectory optimization for the UAV-BS while satisfying QoS requirements. We model the trajectory optimization as an MDP problem and solve it using Q-Learning. Simulation results reveal that our proposed algorithm decreases the average energy consumption by nearly 55% compared to a randomly-served algorithm.

In this paper, we present a new theoretical discovery that the multiple-input and multiple-output (MIMO) capacity can be influenced by atmosphere molecules. In more detail, some common atmosphere molecules, such as Oxygen and water, can absorb and re-radiate energy in their natural resonance frequencies, such as 60 GHz, 120 GHz and 180 GHz, which belong to the millimeter wave (mmWave) spectrum. Such phenomenon can provide equivalent non-line-of-sight (NLoS) paths in an environment that lacks scatterers, and thus greatly improve the spatial multiplexing and diversity of a MIMO system. This kind of performance improvement is particularly useful for most mmWave communications that heavily rely on line-of-sight (LoS) transmissions. To sum up, our study concludes that since the molecular re-radiation happens at certain mmWave frequency bands, the MIMO capacity becomes highly frequency selective and enjoys a considerable boosting at those mmWave frequency bands. The impact of our new discovery is significant, which fundamentally changes our understanding on the relationship between the MIMO capacity and the frequency spectrum. In particular, our results predict that several mmWave bands can serve as valuable spectrum windows for high-efficiency MIMO communications, which in turn may shift the paradigm of research, standardization, and implementation in the field of mmWave communications.

In HTTP-based adaptive streaming systems, media server simply stores video content segmented into a series of small chunks coded in different qualities and sizes. The decision for next chunk's quality level to achieve a high quality viewing experience is left to the client which is a challenging task, especially in mobile environment due to unexpected changes in network bandwidth. Using computer simulations, previous work has demonstrated that Markov decision process (MDP) is very effective for such decision making and that it can reduce video freezing or re-buffering events drastically compared to other methods of adaptation. However, to date there has been no practical implementation and evaluation of MDP-based DASH players. In this work, we extend a publicly available DASH player recently released by DASH industry forum to realise a real DASH player that implements MDP-based video adaptation. We implement two alternative MDP optimisation algorithms, value iteration and Q learning and evaluate their performances in real driving conditions under 300 minutes of video streaming. Our results show that value iteration and Q learning reduce video freezing by a factor of 8 and 11, respectively, compared to the default decision making algorithm implemented in the public DASH player.