No abstract

obile wireless traffic has experienced explosive growth over the past decade, driven largely by the vast application of mobile devices. As application scenarios extended from traditional real-time voice communication to social networks, entertainment, and e-commerce, the number of devices and data rates keep growing exponentially. However, a broad consensus anticipates that the 4G mobile networks will not come close to meeting the demands that networks will face by 2020. Since the wireless link efficiency is approaching fundamental limits, future improvements in the capacity of wireless communication systems can be alternatively achieved by innovation and optimization in network schemes and infrastructures.The 4G/5G wireless networks have been characterized by heterogeneity due to mixed utilization of highly diversified access technologies. Therefore, network operators propose specific requirements to equipment providers for cost-efficient and energy-saving solutions. We introduce some new paradigms to address the above issues, including network function virtualization (NFV), software defined radio (SDR), and software defined network (SDN).First, NFV employs standard IT virtualization technology to consolidate multiple network equipment types onto industry standard high volume servers, switches, and storage devices. In this way, operators can architect networks toward deploying network services onto standard devices [1]. NFV enables delivering network functions without installing hardware equipment for every new service, making possible less investment in network equipment (CAPEX) and less expenditure on network management and operation (OPEX). It enbles the standard network appliance to migrate from one hardware platform to another.Second, SDR aims at implementing many modes by simply reconfiguring the radio with different software, as the name implies. The software may be pre-loaded in the device or downloaded through fixed data links or over-the-air (OTA). SDR has been successfully used in military communication systems and recently introduced to the consumer electronics market [2]. It plays a vital role in military applications with requirements of channel switching and modulation changing. Nowadays, the programmable SDR solution has become attractive as it supports rapid development of wireless standards and a short time to market.Third, SDN allows telecom software developers to control network resources in the same simple way as ordinary computing resources [3]. In order to support the programmability of the network by external applications, SDN addresses the separation of the control plane from the data plane with open interfaces between the centralized controller and packet forwarding devices. On one hand, the software-based controller functions as the control plane and is logically regarded as the core of the network intelligence; on the other hand, the network devices become simple packet forwarding devices representing the data plane.We study the possibility of integrating NFV with SDR/SDN for 4G/5G mo...

No abstract

Through three development routes of authentication, communication, and computing, the Internet of Things (IoT) has become a variety of innovative integrated solutions for specific applications. However, due to the openness, extensiveness and resource constraints of IoT, each layer of the three-tier IoT architecture suffers from a variety of security threats. In this work, we systematically review the particularity and complexity of IoT security protection, and then find that Artificial Intelligence (AI) methods such as Machine Learning (ML) and Deep Learning (DL) can provide new powerful capabilities to meet the security requirements of IoT. We analyze the technical feasibility of AI in solving IoT security problems and summarize a general process of AI solutions for IoT security. For four serious IoT security threats: device authentication, Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks defense, intrusion detection and malware detection, we summarize representative AI solutions and compare the different algorithms and technologies used by various solutions. It should be noted that although AI provides many new capabilities for the security protection of IoT, it also brings new potential challenges and possible negative effects to IoT in terms of data, algorithm and architecture. In the future, how to solve these challenges can serve as potential research directions.INDEX TERMS Artificial intelligence, deep learning, Internet of Things, machine learning, security.

No abstract

Most of the current effective methods for text classification task are based on large-scale labeled data and a great number of parameters, but when the supervised training data are few and difficult to be collected, these models are not available. In this paper, we propose a hierarchical attention prototypical networks (HAPN) for few-shot text classification. We design the feature level, word level, and instance level multi cross attention for our model to enhance the expressive ability of semantic space. We verify the effectiveness of our model on two standard benchmark fewshot text classification datasets-FewRel and CSID, and achieve the state-of-the-art performance. The visualization of hierarchical attention layers illustrates that our model can capture more important features, words, and instances separately. In addition, our attention mechanism increases support set augmentability and accelerates convergence speed in the training stage.

No abstract

Semi-supervised anomaly detection identifies abnormal (testing) observations which are different from normal (training) observations. In many practical situations, anomalies are poorly insufficient and not well defined, while the normal data are easily sampled, have a wide variety, and may not be classified. For this paradigm, we propose a novel end-to-end deep network as an anomaly detector only trained on normal samples. Our architecture consists of a conditional variational auto-encoder (CVAE), a feature discriminator (FD), and an adversarially trained WGAN-GP discriminator. The CVAE is designed as a generator to reconstruct images. It leverages underlying category information and multivariate Gaussian distributions to regularize the latent space, enabling a smooth and informative manifold. For anomalies which have a certain similarity to normal data, we perform active negative training by generating potential outliers from the latent space to limit network generative capability. In order to capture data characteristics, we maximize the mutual information between the inputs and the latent codes by the FD. It enhances the relationship between the high-dimensional image space and corresponding encoded vectors. To promote reconstruction, a structural similarity loss is applied to robustly recover local texture details and the WGAN-GP discriminator is employed to aid in generating photo-realistic images. We distinguish anomalies by computing a reconstruction-based anomaly score. Different from recent encoder-decoder or GAN-based architectures, our approach considers input categories, constructs, and exploits a useful manifold in an unsupervised manner and has a stronger reconstruction capability. The experimental results demonstrate that the proposed approach outperforms state-of-the-art methods over several benchmark datasets. INDEX TERMS Semi-supervised anomaly detection, conditional variational auto-encoder, generative adversarial networks, informative manifold, structural similarity loss.