Radio frequency (RF) fingerprint representing the inherent hardware characteristics of mobile devices has been employed to classify and identify wireless devices for the security of Internet of Things (IoT). Existing works on RF fingerprinting are usually based on the amplitude or phase of RF signal envelope, which leads to relatively coarse features. Moreover, the classification performance over small sample dataset is poor. To solve the problem, a novel device identification method based on RF fingerprinting with on deep learning is proposed. In particular, the RF signal are transformed into two dimensional representations by image preprocessing. Then the gray images representing the RF fingerprints are classified by employing classical CNN. To verify the performance of the proposed approach, a testbed is constructed by using MATLAB build framework of gray image preprocessing. Extensive experiment results show that the identification accuracy can reach at least 90%. Even with the sample rate of 20Gsps. Particularly, the accuracy of iPhone can reach 100%. It is verified that the proposed method can effectively classify mobile devices even with small sample RF fingerprints represented two dimensional gray images,

A virtualized network service is usually realized via one or more service function chain(SFC) composed of a set of VNFs in an ordered sequence. SFC orchestration is critical to efficient 5G/6G service deployment in distributed cloud environment with various constraints such as QoS requirements. In this paper, we address the problem of deployment cost optimization oriented SFC orchestration in the multiple data centers environment with reliability and end-to-end delay constraints. The optimization issue is formulated as a Mixed Integer Linear Programming (MILP) model. Given the NP-hard of the problem, we propose a two-stage approach called Cost-aware, Delay-constrained and Reliability-constrained SFC Orchestration(CDRSO) for the large-scale networks. Extensive simulation results show that CASODP can achieve lower average cost than the existing method CADCSO. Moreover, The CRIM-based backup algorithm performs better than existing CCI-based backup algorithm. Specifically, CDRSO can achieve an average cost nearly 25% lower than CADCSO-CCI, and the acceptance rate is significant higher than CADCSO-CCI. Furthermore, CDRSO constantly outperforms CADCSO-CCI in different reliability requirements and with different SFC lengths.

With the commercial use of the fifth generation (5G), the rapid popularization of mobile Over- The- Top (OTT) voice applications has brought high-quality voice communication methods to users. The intelligent Internet in the 5G era makes communication terminals not limited to mobile phones. The complex communication environment has higher requirements for the security of data transmission between various terminals to prevent the system from being monitored or breached. At present, many OTT users use encrypted proxy technology to get rid of certain restrictions of network operators, prevent their private information from leaking, and ensure communication security. However, in some cases the encryption proxy may be subject to configuration error or maliciously attacked makes the encryption ineffective. The resulting abnormal proxy traffic may cause privacy leakage when users use voice services. However, little effort has been put on fingerprint the effectiveness of encryption for proxy voice traffic in a 5G environment. To this end, we adopt the VGG deep learning method to identify agent speech traffic, compare it with common deep learning methods, and study the impact on model performance with less abnormal traffic. Extensive experimental results show that the deep learning method we use can identify abnormal encrypted proxy voice traffic with the accuracy up to 99.77%. Moreover, VGG outperform other DL methods on indentifying the encryption algorithms of normal encrypted proxy traffic.

Encrypted proxies, such as Shadowsocks and v2ray, are increasingly used to protect user privacy and circumvent censorship. However, the encryption proxies used by some projects may be subject to configuration error or adversary attack makes the encryption ineffective. The resulted abnormal proxy traffic may expose the user’s real network behavior, resulting in user privacy or confidential information leakage. Meanwhile, it is important for network security regulators to identify specific user behaviors from normal encrypted proxy traffics. However, little effort has been put on fingerprinting the encryption validity of proxy traffic. To this end, we employ several typical deep learning methods including Long Short-Term Memory(LSTM), Convolutional Neural Network (CNN) and CNN-LSTM to identify proxy traffic, and investigate the performance and the impact of the sample sizes to these methods. A dataset including normal and abnormal proxy traffic from real network environments is generated to evaluate the performance. Extensive experimental results demonstrate that the mentioned deep learning methods can identify abnormal encrypted proxy traffic with the accuracy up to 99.77%. Moreover, LSTM outperform other DL methods on indentifying the specific user behaviors of normal encrypted proxy traffic.

With the commercialization of fifth-generation (5G), the rapid popularity of mobile Over- The- Top (OTT) voice applications brings huge impacts on the traditional telecommunications voice call service. Tunnel encryption and anonymous network technologies allow OTT users to escape the supervision of network operators easily, which may cause potential security risks to cyberspace. To monitor harmful OTT applications in the context of 5G, it is critical to identify encrypted OTT voice traffic. However, there is no comprehensive study on typical OTT voice traffic identification. This is the first study to analyze OTT Virtual Private Network (VPN) voice traffic in the 5G network specifically. We propose to employ Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to classify encrypted 5G OTT VPN voice traffic, study the impact of the sample sizes and the deep learning methods on identification performance. To verify the performance of the proposed approach, we collect 10 types of typical OTT VPN voice traffic from the experimental 5G network. Extensive experimental results prove the effectiveness of the proposed approach in encrypted 5G OTT VPN voice traffic classification.

In this paper, we propose a physical layer encryption scheme for OFDM-IM systems based on chaotic maps. The chaotic maps are employed not only on the data symbol modulation, but also on the subcarrier index selection. The initial values of the chaotic maps serve as the secret keys, which are extracted from the wireless channel. What's more, the secret key space is large enough to resist the exhaustive attacks. Mathematical analysis and Monte Carlo simulations have been performed to validate the performance of the proposed encryption scheme. Corresponding analysis and simulation results indicate that the proposed encryption scheme outperforms the existing counterparts in terms of security. Meanwhile, the introduce of chaotic maps has no deteriorating effect on reliability. In particular, the needed modification to conventional OFDM-IM systems is minor in our proposed scheme.

Recently, device-to-device (D2D) enabled non-orthogonal multiple access (NOMA) is emerged as a new paradigm to improve spectrum efficiency. However, existing researches are confined to two-hop relaying scenarios, which restricts the coverage of the wireless networks. In this paper, we propose a novel multi-hop relaying scheme where both D2D transmitter and receiver are used as relays. Further, the cell-edge user employs maximal ratio combing (MRC) to enhance the quality of the received signal, of which the analysis becomes more complicated. Exact new closed-form expressions are provided for the cumulative distribution functions (CDFs) of the received signal-to-interference-plus-noise-ratio (SINR) at all users. Analysis on outage probability and ergodic capacity is presented and validated by simulations. It is demonstrated that the proposed scheme significantly outperforms typical two-hop relaying schemes.

Nowadays, increasing Android applications attempt to obtain a large number of sensitive user information such as Contacts, SMS, Call logs, IMEI, IMSI without rational necessity, which has seriously threatened the privacy of users. However, the existing Android cannot effectively prevent the above risks. To solve this problem, this paper proposes a novel, user-driven sensitive information management model-UIDroid. UIDroid redefines the subject, object, definition of security level, legitimacy of operations, and system security status. With UIDroid, users could authorize the sub-functions of an application to access sensitive information with rational security levels based on essential requirements on the accuracy of the sensitive data. The prototype of UIDroid is developed to verify the feasibility of the UIDroid and compatibility with existing applications. Extensive experiments show that UIDroid can effectively prevent malicious applications from getting unnecessary sensitive user information with unnecessary accuracy. Meanwhile, the overall performance overhead introduced by UIDroid is less than 4.8%.

6G is expected to support the unprecedented Internet of everything scenarios with extremely diverse and challenging requirements. To fulfill such diverse requirements efficiently, 6G is envisioned to be space-aerial-terrestrial-ocean integrated three-dimension networks with different types of slices enabled by new technologies and paradigms to make the system more intelligent and flexible. As 6G networks are increasingly complex, heterogeneous and dynamic, it is very challenging to achieve efficient resource utilization , seamless user experience , automatic management and orchestration. With the advancement of big data processing technology, computing power and the availability of rich data, it is natural to tackle complex 6G network issues by leveraging artificial intelligence (AI). In this paper, we make a comprehensive survey about AI-empowered networks evolving towards 6G. We first present the vision of AI-enabled 6G system, the driving forces of introducing AI into 6G and the state of the art in machine learning . Then applying machine learning techniques to major 6G network issues including advanced radio interface , intelligent traffic control, security protection, management and orchestration, and network optimization is extensively discussed. Moreover, the latest progress of major standardization initiatives and industry research programs on applying machine learning to mobile networks evolving towards 6G are reviewed. Finally, we identify important open issues to inspire further studies towards an intelligent, efficient and secure 6G system.

A virtualized network service is generally implemented via a service function chain(SFC) composed of a set of VNFs in an ordered sequence. The SFC orchestration aims to deploy SFCs on limited and distributed cloud infrastructures with various optimization targets while guaranteeing QoS requirement of the network service. In this paper, we address the problem of SFC orchestration in the multiple data centers aiming at minimizing deploying cost with delay constraint. Especially, we take into account the impact of VNFs on the link cost and multiple ingresses/egresses of SFCs. We formulate the problem as a Mixed Integer Linear Programming (MILP) model and propose a heuristic algorithm called Cost-Aware and Delay-Constrained SFC Orchestration (CADCSO) to the problem. Extensive simulation results show that CADCSO can achieve near-optimal results with much less time in small-scale network environments. Compared with the existing solution CASO, CADCSO can reduce the average cost by at least 30% and increase the acceptance ratio by around 23% in large-scale network environments. Furthermore, CADSCO outperforms CASO significantly in the case of multiple ingresses/egresses.

In this paper, a novel framework for cluster detection in co-operative wireless networks is proposed. This framework is modeled by a dynamic game with incomplete information, in which each player in the game aspires to improve its position in the network by forming cooperative groups. Instead of static systems, the attention we paid in this paper is highly dynamic networks, where the users' high mobility brings a huge challenge in clustering. In order to mitigate that impact, this paper is from the perspective of social relations to clustering, extracting users' social nature from their mobile patterns and designing distributed cluster strategy based on game model. The introduction of social nature with generally long-term characteristics makes clustering framework more predictive and stable. Simulations on real-world networks show that the proposed approach performs well in clustering in cooperative wireless networks.

Given the rising concerns on carbon emission and increasing operating expense pressure, mobile network operators and device vendors are actively driving the energy‐efficient network evolution. Energy efficiency (EE) has been determined as one of the key objectives of the 5G system. To realise sustainable 5G, various new technologies have been proposed to reduce conventional energy consumption. Meanwhile, green energy sources are explored to reduce the dependence on conventional energy. This study makes a survey on recent academia and industry research on the EE of the 5G system from perspectives of radio resource management, architecture and deployment paradigm, green energy harvesting and smart grid integration. Typical green 5G enabling technologies are presented and discussed comprehensively. Moreover, the latest progress on EE in 3GPP is also investigated. Given the broad research areas, only those critical open issues and challenges are presented to inspire further investigations. Finally, the authors identify several research directions as the way forward to realise the green 5G system.

The two-way training discriminatory channel estimation (DCE) for non-reciprocal wireless MIMO channels can efficiently differentiate the performance at the legitimate receiver (Bob) and the eavesdropper (Eve). Eve's channel estimation performance is deliberately degraded by the artificial noise (AN) inserted into the training sequence. However, it ignores the possibility that Eve can derive any useful information which can be used to reduce the AN interference during the round-trip stage. In this paper, we discuss the feasibility that Eve can derive certain helpful information from its observations during the two-way training DCE. Then, we propose a pseudo downlink channel (PDC) scheme for Eve to improve its channel estimation performance, which collapses the security of legitimate receiver.

As a promising interference management technique, interference alignment (IA) was proposed for improving system capacity and spectral efficiency by precoding and filtering design. However, the previous works assumed the equal power allocation among data streams in IA‐based networks, and the sum‐rate may fall short of the theoretical maximum without the energy‐efficient optimisation. In this study, a novel approach (two‐game theoretic) is presented, to solve the rate maximisation problem in the IA‐based uplink multiple‐input multiple‐output cellular networks. First, a two‐game analytical framework is presented, where the IA design and power allocation are modelled as two game processes, respectively, and the authors prove that both games have Nash equilibrium solutions. Second, based on the framework, two iterative algorithms of joint IA and power allocation that achieve the maximum sum‐rate are proposed. In addition, the authors analyse the sum‐rate performance loss under imperfect channel state information (CSI), which depends on the variance of CSI error. Simulation reveals that the sum‐rate performances of the proposed iterative algorithms are higher than that of the previous schemes at low signal‐to‐noise ratio, whose computational complexities are acceptable.

Device-to-Device (D2D) is a popular technology to improve the utilization of network resources, but the interference in D2D networks with Cellular Networks is much larger than that in traditional cellular networks with the spectrum-sharing. In this paper, we propose an iterative interference alignment (IA) algorithm for D2D Local Area Network (LAN) with the cellular networks. To maximize the power of desired signal, the algorithm optimizes the pre-coding vector and the post-processing matrix alternately. Numerical results and analysis turn out that the sum-rate performance of the proposed algorithm is superior to the existed interference management methods at the middle to high signal to noise ratio (SNR) scenarios. Moreover, the algorithm shows fast convergence and can be converged after five iterations.

As mobile networks are witnessing huge growth in the volumes of data traffic from smartphone and tablet. Mobile operators start to look into CDN and caching in order to offload increasingly overloaded mobile networks, reduce network and peering cost, and improve mobile user's quality of experience. For CDN and cache deployment in mobile network, one practical issue is where to deploy CDN or cache function. As mobile network is designed as a tiered and hierarchical structure, the cache or CDN function could be placed at multiple potential points, e.g., GGSN, RNC and etc. In this paper, we propose an economic model that can be used to analyze the cost saving and benefit when cache function is place at different places of mobile network. A real mobile network is studied according to this model. We can see that the best place to store the cached content really depends on the network infrastructure and cost composition of the mobile operator. In addition, other issues, like technical complexity and performance, shall be considered together.