The Internet-of-Things (IoT) becomes a novel paradigm as more and more devices are connected to the Internet, enabling several innovative applications such as smart home, industrial automation, and connected health. However, the cyber-attack to these applications is a big issue and countermeasures are in dire need to provide system security and user privacy. In this paper, we address the traffic analysis attack to smart homes, where adversaries intercept the Internet traffic from/to the smart home gateway and profile residents’ behaviors through digital traces. Traditional cryptographic tools may not work well due to the effectiveness of adversaries’ machine learning algorithms in classifying encrypted traffic, so here we propose a privacy-preserving traffic obfuscation framework to achieve the goal. To be specific, we leverage the smart community network of wirelessly connected smart homes and intentionally direct each smart home’s traffic to another home gateway before entering the Internet. The design jointly considers the network energy consumption and the resource constraints in IoT devices, while achieving strong differential privacy guarantee so that adversaries cannot link any traffic flow to a specific smart home. Besides, we consider a hostile smart community network and develop secure multi-hop routing protocols to guarantee the source/destination unlinkability and satisfy each user’s personalized privacy requirement. To evaluate the effectiveness of our framework in protecting privacy and reducing network energy consumption, extensive simulations are conducted and the results demonstrate that our design outperforms other differential privacy mechanism in preserving privacy and minimizing network utility cost.

Federated learning (FL) is a popular collaborative distributed machine learning paradigm across mobile devices. However, practical FL over resource constrained mobile devices confronts multiple challenges, e.g., the local on-device training and model updates in FL are power hungry and radio resource intensive for mobile devices. To address these challenges, in this paper, we attempt to take FL into the design of future wireless networks and develop a novel joint design of wireless transmission and weight quantization for energy efficient FL over mobile devices. Specifically, we develop flexible weight quantization schemes to facilitate on-device local training over heterogeneous mobile devices. Based on the observation that the energy consumption of local computing is comparable to that of model updates, we formulate the energy efficient FL problem into a mixed-integer programming problem where the quantization and spectrum resource allocation strategies are jointly determined for heterogeneous mobile devices to minimize the overall FL energy consumption (computation + transmissions) while guaranteeing model performance and training latency. Since the optimization variables of the problem are strongly coupled, an efficient iterative algorithm is proposed, where the bandwidth allocation and weight quantization levels are derived. Extensive simulations are conducted to verify the effectiveness of the proposed scheme.

As an important technology in the field of Internet of Things, activity recognition is a well-researched topic. Due to its characteristics of no-invasion, no privacy leakage, good user experience, and high recognition accuracy rate, Channel State Information (CSI)-based method is one of the most widely used approaches for the activity recognition problem. However, the commodity WiFi devices for identification are usually in a complex electromagnetic environment, where the interference caused by WiFi devices from channel overlap is common and severe. Furthermore, our extensive experiments show that the performance of the state-of-the-art recognition systems may degrade significantly with co-channel interference (CCI). To solve the above problem, we propose WiAnti, a CSI-based activity recognition system which is robust to CCI. Two adaptive subcarrier selection algorithms, WiAnti-Pearson and WiAnti-DTW, are proposed to mitigate the impact of CCI and to improve the activity recognition performance. As demonstrated in the experimental results, WiAnti-Pearson yields 95% activity recognition accuracy rate on average, which can improve up to 14% recognition accuracy rate in the presence of constant CCI. Moreover, WiAnti-DTW achieves 8% higher recognition accuracy rate in the scenario with varying CCI, reaching 94%.

Hybrid free-space optical (FSO)/radio-frequency (RF) communication has emerged as an effective solution for high-data-rate wireless transmission. In this paper, multiuser diversity over parallel and hybrid FSO/RF links is discussed. We present and analyze a hybrid FSO/RF point-to-multipoint system that consists of a hybrid access point (HAP), multiple FSO users, and multiple RF users. Either an FSO user or an RF user is scheduled to communicate with HAP at each transmission block. We propose a link quality scheduling strategy. The statistical characterizations of the proposed strategy are derived. Based on these characterizations, the outage probability and the average bit error rate are also analyzed. Novel asymptotic closed-form expressions at high signal to noise are derived. The multiuser diversity gain and diversity order for this scheduling strategy are further discussed. Numerical results are given to validate all the analytical results.

Dynamic spectrum access (DSA) is the key to solving worldwide spectrum shortage. The open wireless medium subjects DSA systems to unauthorized spectrum use by illegitimate users. Secondary-user authentication is thus critical to ensure the proper operations of DSA systems. This paper presents SpecGuard, the first crowdsourced spectrum misuse detection framework for DSA systems. In SpecGuard, a transmitter is required to embed a spectrum permit into its physical-layer signals, which can be decoded and verified by ubiquitous mobile users. We propose three novel schemes for embedding and detecting a spectrum permit at the physical layer. The first scheme relies on a higher transmission power to embed the spectrum permit. To alleviate the assumptions on the additional transmission power, the second scheme is proposed with a limited negative impact on the normal data transmission. The third scheme takes a different approach by adopting a novel constellation design and exploiting the trust between the transmitter and the receiver. Crowdsourced spectrum misuse detection eliminates the need for the deployment of dedicated sensors and thus greatly reduces the deployment and maintenance cost. Detailed theoretical analyses, MATLAB simulations, and USRP experiments confirm that our schemes can achieve correct, low-intrusive, and fast spectrum misuse detection.

The exponential growth of Internet of Things (IoT) devices and emerging applications have significantly increased the requirements for ubiquitous connectivity and efficient computing paradigms. Traditional terrestrial edge computing architectures cannot provide massive IoT connectivity worldwide. In this paper, we propose an aerial hierarchical mobile edge computing system composed of high-altitude platforms (HAPs) and unmanned aerial vehicles (UAVs). In particular, we consider non-divisible tasks and formulate a task offloading problem to minimize the long-term processing cost of tasks while satisfying the queueing mechanism in the offloading procedure and processing procedure of tasks. We propose a multi-agent deep reinforcement learning (DRL) based computation offloading algorithm in which each device can make its offloading decision according to local observations. Due to the limited computing resources of UAVs, high task loads of UAVs will increase the ratio of abandoning offloaded tasks. To increase the success ratio of completing tasks, the convolutional LSTM (ConvLSTM) network is utilized to estimate the future task loads of UAVs. In addition, a prioritized experience replay (PER) method is proposed to increase the convergence speed and improve the training stability. The experimental results demonstrate that the proposed computation offloading algorithm outperforms other benchmark methods.