Federated learning (FL) is a distributed machine learning (ML) technique that allows numerous Internet of Things (IoT) devices to jointly train an ML model using a centralized server for help. Local data never leaves each IoT device in FL, so the local data of IoT devices are protected. In FL, distributed IoT devices usually collect their local data independently, so the data set of each IoT device may naturally form a distinct source domain. In real-world applications, the model trained over multisource domains may have poor generalization performance on unseen target domains. To address this issue, we propose federated adversarial domain generalization (FedADG) to equip FL with domain generalization capability. FedADG employs the federated adversarial learning approach to measure and align the distributions among different source domains via matching each distribution to a reference distribution. The reference distribution is adaptively generated (by accommodating all source domains) to minimize the domain shift distance during alignment. Therefore, the learned feature representation tends to be universal, and, thus, it has good generalization performance over the unseen target domains while protecting local data privacy. Intensive experiments on various data sets demonstrate that FedADG has comparable performance with the state-of-the-art.

The prediction of taxi-passenger’s destination with the partial GPS trajectory left by moving taxis is an important yet challenging research issue. The high uncertainty of human mobility and limited clue provided by the unfinished trajectory are two major barriers to developing effective predictors. In general, such a prediction task is often converted to the identification one among given candidate destinations. Hence, how to extract the discriminative knowledge from the partial trajectory becomes crucial. It is well-recognized that the sequence of visited locations by the taxi has inherent relationship with the heading destination. Inspired by the idea, we propose a novel approach that jointly combines the GPS embedding and attention-based BiLSTM techniques for the prediction of passenger’s destination. Specifically, we propose two GPS embedding methods to encode the geographic proximity and multi-scale spatiality of GPS points into embedding vectors, so as to reveal the spatial context of visited locations in the urban space. After converting GPS trajectories into embedding sequences, we further establish an attention-based dual BiLSTMs neural network to model the relationship between the heading destination and the bidirectional sequential context of visited locations. Meanwhile, the discriminative capability of visited locations in determining the destination can be captured by the attention mechanism. In addition, the OT (origin and time) information is aggregated into the neural network as auxiliary features. Stepping closer to smarter passenger services, rather than telling destinations in terms of drop-off clusters, our proposed model outputs the destinations in terms of historical passengers’ destination clusters. Finally, we evaluate the system performance based on two real large-scale datasets. Results show the superior performance of our proposed model.

Internet of Medical Things (IoMT) technologies significantly improve the quality of health care, especially at the time when COVID-19 is becoming a worldwide pandemic. Due to the complexity of devices and user nodes in the IoMT system, there should be some ways to ensure the security and quality of the service or information. Decentralized trust management techniques are efficient means of promoting application security and reliability in these cases. However, the majority of currently utilized access control schemes cannot be applied in decentralized trust management systems or perform poorly owing to the numerous restrictions of decentralized systems. In this paper, we present a policy-hiding and multi-authority key generation CP-ABE scheme (PM-CPABE) for decentralized trust management systems, which could provide fine-grained access control capabilities. Meanwhile, the proposed scheme does not require any fully trusted entity, thus it can be well adapted to decentralized trust management systems. The scheme also implements policy hiding to protect user privacy. In addition, it supports large universe and outsourced decryption. The security analyses and performance comparisons give evidence of our scheme is security and efficient.

As a new paradigm to serve and sense the intelligent city, mobile crowd-sensing (MCS) usually requires participants' real-time locations. However, uploading participants' true locations to servers or third parties raises privacy concerns. In this letter, we propose a real-time data collection mechanism with trajectory privacy (RDCTP) in MCS, which achieves w-event a-differential privacy for the crowd-sensing participants. Different from existing works, we focus on protecting the privacy of trajectories instead of individual locations. Specifically, RDCTP provides a-differential privacy for each sub-trajectory which consists of successive w locations. To achieve this, a participant first allocates the trajectory privacy budget to each location. Then, he perturbs his true location and gets candidate location set which satisfies a-differential privacy. Last, he submits a location from the set by solving an optimization problem that aims to tradeoff between the privacy and utility. We utilize real world traffic trajectories of Shanghai taxis to evaluate the RDCTP, and the results show that it not only protects participants' privacy, but also preserves the server's utility.

Accurate traffic prediction is a critical yet challenging task in Intelligent Transportation Systems, benefiting a variety of smart services, e.g., route planning and traffic management. Although extensive efforts have been devoted to this problem, it is still not well solved due to the flexible dependency within traffic data along both spatial and temporal dimensions. In this paper, we explore the flexibility from three aspects, namely the time-varying local spatial dependency, the dynamic temporal dependency, and the global spatial dependency. Then we propose a novel Dual Graph Gated Recurrent Neural Network (DG²RNN) to effectively model all these dependencies and offer flexible (multi-step) predictions for future traffic flow. Specifically, we design a Dual Graph Convolution Module to capture the local spatial dependency from two perspectives, namely road distance and adaptive correlation. To model the dynamic temporal dependency, we firstly develop a Bidirectional Gated Recurrent Layer to capture the forward and backward sequential contexts of historical traffic flow, then combine the derived hidden states with their various contributions learned by a temporal attention mechanism. Besides, we further design a spatial attention mechanism to learn the latent global spatial dependency among all locations to facilitate the prediction. Extensive experiments on three types of real-world traffic datasets demonstrate that our model outperforms state-of-the-arts. Results also show our model has more stable performance for the flexible prediction with varying prediction horizons.