Powered by a number of smart devices distributed throughout the whole network, the Internet of Things (IoT) is supposed to provide services computing for massive data from devices. Fog computing, an extension of cloud-based IoT-oriented solutions, has emerged with requirements for distribution and decentralization. In this respect, the conjunction with Blockchain provides a natural solution for decentralization, as well as potentially helps fog computing overcome some deficiencies such as security and privacy then consequently expand the application scope of IoT. However, one of the key challenges of blockchain's integration with fog computing is scalability. To end this, this work proposes Groupchain, a novel scalable public blockchain of a two-chain structure suitable for fog computing of IoT services computing. Groupchain employs the leader group to collectively commit blocks for highertransaction efficiency and introduces bonus and deposit into the incentive mechanism to supervise behaviors of members in the leader group. Our security analysis shows that Groupchain retains the security of Bitcoin-like blockchain and enhances defense against attacks such as double-spend and selfish mining. We implement a prototype of Groupchain and conducted experiments. The experimental results demonstrate that Groupchain achieves optimization on transaction throughput and confirmation latency which are argued in Bitcoin.

Recent artificial intelligence research has witnessed great interests in automatically generating text descriptions of images, which is known as the image captioning task. Remarkable success has been achieved on domains where a large number of paired data in multimedia is available. Nevertheless, annotating sufficient data is labor-intensive and time-consuming, establishing significant barriers for adapting the image captioning systems to new domains. In this study, we introduce “MLADIC”, a novel Multitask Learning Algorithm for cross-Domain Image Captioning. MLADIC is a multitask system that simultaneously optimizes two coupled objectives via a dual learning mechanism: image captioning and text-to-image synthesis, with the hope that by leveraging the correlation of the two dual tasks, we are able to enhance the image captioning performance in the target domain. Concretely, the image captioning task is trained with an encoder-decoder model (i.e., CNN-LSTM) to generate textual descriptions of the input images. The image synthesis task employs the conditional generative adversarial network (C- GAN) to synthesize plausible images based on text descriptions. In C-GAN, a generative model G synthesizes plausible images given text descriptions, and a discriminative model D tries to distinguish the images in training data from the generated images by G. The adversarial process can eventually guide G to generate plausible and high-quality images. To bridge the gap between different domains, a two-step strategy is adopted in order to transfer knowledge from the source domains to the target domains. First, we pre-train the model to learn the alignment between the neural representations of images and that of text data with the sufficient labeled source domain data. Second, we fine-tune the learned model by leveraging the limited image-text pairs and unpaired data in the target domain. We conduct extensive experiments to evaluate the performance of MLADIC by using the MSCOCO as the source domain data, and using Flickr30k and Oxford-102 as the target domain data. The results demonstrate that MLADIC achieves substantially better performance than the strong competitors for the cross-domain image captioning task.

Heterogeneous Internet of Things (IoT) and multi-access mobile edge computing (MA-MEC) are believed as supporting technologies for building smart city. The advancement and flourish of IoT are facilitating the entry of human society into the Internet of everything era, which lay the foundation of smart city. To address the conflict between computation capability and low-cost mobile devices in IoT, MA-MEC is available for supporting the resource-limited and computation-sensitive services and applications by computation offloading and distributed content delivery/caching, etc. However, deploying cloud computing capability within radio access network may face serious security threats which stem from not only the existing technologies and networks but also the MA-MEC based IoT itself. Therefore, the solutions to address the security threats are investigated in this paper from physical layer perspectives, since physical layer security technologies have the advantages of achieving perfect secrecy, low computational complexity and resource consumption, and good adaptation for channel changes. Specifically, we investigate the secure wiretap coding, resource allocation, signal processing, and multi-node cooperation, along with physical layer key generation and authentication, to cope with the emerging security challenges. Finally, the paper is concluded with some possible future research directions.