AuthCODE: A privacy-preserving and multi-device continuous authentication architecture based on machine and deep learning

With rapid growth of mobile users and developents of mobile equipments like cell phones, laptops and personal digits assistances (PDA), mobile networks have to meet dramatically increased service demands in the nearest future. The ever-increasing demands, such as the users expect to enjoy the service anywhere, anytime and the networks support a seamless mobility, driving the evolution of mobile networks at a fast pace. The next generation mobile network (LTE in 3GPP) is conducting research towards this goal. An IP protocol based flatter network architecture has been introduced in the next generation mobile networks (NGMN). In this network architecture, gateway (GW) is the only node which establishes a connection between RAN and external world. To provide capabilities of gateways catering for service demand at different stages, more advanced functions such as load balancing between gateways is proposed. Such mechanism will be used as a solution to avoid gateways congestion and optimize network performance for the future network. In this paper, based on the described flat architecture of the next generation mobile networks and some related concepts such as the pool of gateway, inter-GW load balancing approach has been introduced followed by performance evaluation. Simulation results show promising gains provided by the inter-GW load balancing mechanism for next generation systems.

Next Generation Mobile Networks (NGMN) will be able to deliver voice calls, video streams, website visits, data services, and other services all through the same device on a transparent network, as opposed to the current generation of wireless communications. NGMN Alliance solutions are designed to improve service delivery while reducing the costs for both service providers and end-users.

This paper proposes a security control framework for mitigating epidemic and pandemic network attacks in Next Generation Mobile Networks (NGMN) by adopting several interesting principles from the human immune system (HIS) and the field of epidemiology. In particular, the proposed framework incorporates two key components: namely, the attack localization process and the attack recovery process. While the former administers the autonomous attack mitigation process and the security updates procedure, the latter accommodates a last line of defense (in the form of quarantine and rate limiting) for preventing repeated attacks on the NGMN. Performance evaluation indicates that the proposed security control framework is efficient in restricting both epidemic and pandemic attacks, and effective in alleviating the impact of the attacks on the network, thereby enhancing the survivability of the NGMN.

Seamless access to video services in Next Generation Mobile Networks (NGMNs) introduces new challenges in the video quality provisioning. Terminal mobility and network handover affect the Quality of Service (QoS) and the perception of the mobile users. To improve the Quality of Experience (QoE) in NGMNs, cross-layer adaptation of the video streaming is required. A technique to replace the applied video codec during ongoing real-time video transmissions, such as video call, is described in this paper. The presented solution enables to seamlessly switch between the video codecs independently from the applied coding schemes, allows to maintain ongoing sessions, and helps to reduce the changeover-related artifacts to a large degree. The proposed algorithm has been implemented and evaluated in a NGMN testbed. The technique enabled to significantly improve user perception during wireless transmission affected by packet loss, and performed best as compared to network handover and video bit rate reduction that are considered as alternative quality adaptation measures. This proves the relevance of the presented codec changeover solution for video quality provisioning in mobile networks.

In order to augment the efficacy of the intelligent evaluation model for assessing the suitability of ice and snow tourism, this study refines the model by incorporating the Long Short-Term Memory (LSTM) network within the framework of the Internet of Things (IoT). The investigation commences with an elucidation of the application of IoT technology in environmental detection. After this, an analysis is conducted on the structure of LSTM and its merits in the realm of time series prediction. Ultimately, a novel model for appraising the suitability of ice and snow tourism is formulated. The efficacy of this model is substantiated through empirical experiments. The results of these experiments reveal that the refined model exhibits exceptional performance across diverse climatic conditions, encompassing mild, cold, humid, and arid climates. In regions characterized by mild climates, the predictive accuracy of the refined model progressively ascends from 88% in the initial quarter to 94% in the fourth quarter, surpassing the capabilities of conventional models. Consistently robust performance is demonstrated by the refined model throughout each quarter. In terms of operational efficiency, comparative analysis indicates that the refined model attains a moderate level, manifesting a 30–33 s runtime and maintaining a Central Processing Unit (CPU) usage rate between 40 and 43%. This observation implies that the refined model adeptly balances precision against resource consumption. Consequently, this study holds significance as a scholarly reference for the integration of IoT and LSTM networks in the domain of tourism evaluation.

The emergence of the Internet of things (IoT), web of things, when heterogeneous devices need to have access to the Internet, leads to the need to solve serious problems to ensure the reliable and security operation of such devices. Developing a model of the IoT system states in conditions of growing attacks on the IoT infrastructure, taking into account the energy spent on round-the-clock maintenance of the IoT system, and the timely installation of patches for the router's firewall software, will allow investigating the IoT systems availability from the point of view of providing their security and energy efficiency. The purpose of this paper is to improve the availability model of Smart Office (SO) and to investigate it in terms of server and router power modes, router and server faults and failures, successful cyber-attacks and timely installation of patches on possible router firewall vulnerabilities.

We consider the problem of signaling rate and performance for control and management of reconfigurable intelligent surfaces (RISs) in next-generation mobile networks. To this end, we first analytically determine the rates of RIS reconfigurations and handover using a stochastic geometry network model. We derive closed-form expressions of these rates, while taking into account static obstacles (both known and unknown), self-blockage, RIS location density, and variations in the angle and direction of user mobility. Based on the derived rates, we analyze the signaling rates of a sample novel signaling protocol, which we propose as an extension of the current handover signaling protocol. We evaluate the signaling overhead due to RIS reconfigurations and the related energy consumption. We also provide a capacity planning analysis of the related RIS control plane server for its dimensioning in the network management system. The results quantify the impact of known and unknown obstacles on the RIS reconfiguration rate and the handover rate as a function of device density and mobility. We evaluate the scalability of the model, the related signaling overhead, energy efficiency, and server capacity in the control plane. To the best of our knowledge, this is the first analytical model to derive the closed form expressions of RIS reconfiguration rates, along with handover rates, and relate its statistical properties to the signaling rate and performance in next-generation mobile networks.

The proliferation of Internet of Things (IoT) devices in smart industrial contexts necessitates robust security measures to thwart potential threats. This study addresses the escalating security challenges arising from the widespread deployment of IoT devices in smart industrial environments. Focusing on the identification and categorization of potentially harmful activities, our research introduces an innovative framework that seamlessly integrates networks of Extreme Learning Machines (ELM) with Long Short-Term Memory (LSTM). The primary goal is to significantly enhance the accuracy and efficiency of real-time detection of suspicious activities. Implemented using Python, the framework exhibits a remarkable 97.5% improvement in recognizing and accurately categorizing suspicious activities compared to traditional methods such as Conv 1D and 3D CNN. Rigorous testing on a substantial real-world dataset simulating smart industry scenarios underlines this substantial improvement over conventional approaches in identifying and precisely classifying questionable activities. The design excels in comprehending complex behavioral trends within the dynamic IoT data environment, leveraging the temporal memory retention capacity of LSTM networks. This research lays the groundwork for fortifying cybersecurity in smart industries against emerging online threats and malicious actions. The proposed framework capitalizes on the synergies between LSTM and ELM networks to achieve heightened accuracy in identifying suspicious activities, providing comprehensive and dynamic insights from real-time IoT data. These insights are crucial for proactive threat detection and prevention in smart industrial settings, contributing to an elevated level of security against evolving threats.

Leaf wetness duration (LWD), soil moisture, soil temperature, ambient temperature, and relative humidity information are the essential factors that leads to germination of plant disease. In this work, an internet of things (IoT) enabled leaf wetness sensor (LWS) and soil moisture sensor (SMS) is developed. Subsequently, commercial soil temperature (ST), relative humidity (RH) and ambient temperature (AT) are used for plant disease prediction. The developed LWS offers a response of about 250% when exposed to air and water and response time of about 20 seconds and attributes a hysteresis of about ±3 %. Acrylic protective lacquer (APL) coating of about 25- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$75 ~\mu \text{m}$ </tex-math></inline-formula> thin is deposited on LWS and it is observed that the sensor capacitance changes only by 2% when temperature varies from 20 °C to 65 °C. Likewise, fabricated SMS offers a response of 10 kHz ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol {\Delta } \text{F}$ </tex-math></inline-formula> ) with only a 2% change in frequency when temperature varies from 20 °C to 65 °C and works with an accuracy of ±3%. Further, aforementioned sensors along with in-house developed IoT-enabled system has been deployed under field conditions for about four months. In this work, we considered Powdery mildew (D1), Anthracnose (D2), and Root rot (D3) disease on the Mango plant. Further, we have implemented the Long Short Term Memory (LSTM) network which performs better compared to the existing methods discussed on plant disease management. The proposed network achieves an accuracy of 96%, precision-recall and F1 score of 97%, 98%, and 99%, respectively.

Smart Offices promise the improvement of working conditions in terms of efficiency, productivity and facility. However, new cybersecurity challenges arise associated with the new capabilities of Smart Cities. One of the key challenges is the utilisation of continuous and non-invasive authentication mechanisms since traditional authentication methods have important limitations. Thus, to cover these limitations, the main contribution of this paper is the design and deployment of a continuous and intelligent authentication architecture oriented to Smart Offices. The architecture is oriented to the cloud computing paradigm and considers Machine Learning techniques to authenticate users according to their behaviours. Some experiments demonstrated the suitability of the proposed solution when recognising and authenticating different users using a classification algorithm.

Cloud radio access network is one of the most promising cellular networks for the next generation of mobile networks. The basic idea of cloud RAN (radio access network) is virtualizing and centralizing the intelligent part of the base station, the base band unit, and keeping remote radio heads on cell site enabling a centralized processing and management. Offloading data computation to edge cloud was proposed as a solution to deal with resource limitation while keeping a good quality of service. In this paper, we propose a strategy to jointly handle offloading decision and offloading request scheduling in cloud RAN. We aim to improve network quality of service while reducing the scheduling cost expressed in terms of overload, network delay, and migration cost. Numerical results show that the proposed approach is able to reduce the response time of the applications, mobile terminal energy consumption, and total execution cost.

With the development of the next generation of mobile networks, new research challenges have emerged, and new technologies have been proposed to address them. On the other hand, reconfigurable intelligent surface (RIS) technology is being investigated for partially controlling wireless channels. RIS is a promising technology for improving signal quality by controlling the scattering of electromagnetic waves in a nearly passive manner. Heterogeneous networks (HetNets) are another promising technology that is designed to meet the capacity requirements of the network. RIS technology can be used to improve system performance in the context of HetNets. This study investigates the applications of reconfigurable intelligent surfaces (RISs) in heterogeneous downlink networks (HetNets). Due to the network densification, the small cell base station (SBS) interferes with the macrocell users (MUEs). In this paper, we utilise RIS to mitigate cross-tier interference in a HetNet via directional beamforming by adjusting the phase shift of the RIS. We consider RIS-assisted heterogeneous networks consisting of multiple SBS nodes and MUEs that utilise both direct paths and reflected paths. Therefore, the aim of this study is to maximise the sum rate of all MUEs by jointly optimising the transmit beamforming of the macrocell base station (MBS) and the phase shift of the RIS. An efficient RIS reflecting coefficient-based optimisation (RCO) is proposed based on a successive convex approximation approach. Simulation results are provided to show the effectiveness of the proposed scheme in terms of its sum rate in comparison with the scheme HetNet without RIS and the scheme HetNet with RIS but with random phase shifts.

Owing to the limitation in bandwidth of currently used frequency bands, future fifth generation (5G) mobile networks will need to operate at higher frequencies. However, one important step in the research activities for the next generation of mobile networks is the broadband fully polarimetric analysis of the multipath propagation in dynamic single and multiuser scenarios under time-variant shadowing environments in millimetre- wave (mm-wave) channels. This paper presents a channel sounding campaign at 70 GHz in an urban outdoor scenario focusing on broadband channel characteristic at mmwave. For the measurements a novel dual-polarized (DP) ultrawideband (UWB) multi-channel sounder (DP-UMCS) architecture, developed at the TU Ilmenau for propagation measurements in cellular networks, was used to study the directional and polarization properties of the channel in view of the future wireless communication systems.

In order to support a wide range of data transfer and user applications, mobility management becomes a crucial factor when designing infrastructure for wireless mobile networks. Mobility management requests are often initiated either by a mobile terminal movement (crossing a cell boundary) or by deterioration in the quality of a received signal on a currently allocated channel. Due to the anticipated increase in the usage of the wireless services in the future, the next generation of mobile networks should be able to support a huge number of users and their bandwidth requirements.The talk will address some of the key algorithmic and computational challenges associated with the mobility management problem. The talk will present several scenarios for static and dynamic mobility management instances incorporating a combination of metaheuristics. The studies show that hybrid approaches are more capable at producing efficient solutions. From a practical standpoint, these approaches have the potential to lead to massive savings in the number of network signal transactions made to locate users. Several hybrid approaches are used with a number of test networks to show their advantages to the currently implemented GSM standards. The results provide new insights into the mobility management problem.

The next generation of mobile networks is expected to utilize multiple radio access technologies (RAT), seamlessly integrated to form a heterogeneous wireless network. On the arrival of service request, an access network must be assigned to the user. A request can be due to a new connection call within a cell, an intra- system or inter-system handover attempt. In case of handoff, it must be realized as fast as possible. However, some factors as the authentication service has an important impact on the final handover latency. The problem is increased in the case of vertical handover. This paper describes the reference architecture for access management in which the handovers take place; we measure the handover latency and we make an analysis of the impact that the authentication procedure has in the final delay of the handover execution on heterogeneous mobile communication networks.