Fig 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
![Registration and authentication process as defined by FIDO [11]](publication/361626589/figure/fig9/AS:11431281094020697@1667352820441/Registration-and-authentication-process-as-defined-by-FIDO-11.png)
Source publication
![Fig. 1. Registration and authentication process as defined by FIDO [11]](publication/361626589/figure/fig9/AS:11431281094020697@1667352820441/Registration-and-authentication-process-as-defined-by-FIDO-11_Q320.jpg)
The traffic from the large number of IoT devices connected to the IoT is a source of congestion known as the Massive Access Problem (MAP), that results in packet losses, delays and missed deadlines for real-time data. This paper reviews the literature on MAP and summarizes recent results on two approaches that have been designed to mitigate MAP. On...
Similar publications
Citations
... Massive IIoT networks face several critical challenges, including wireless channel overload, packet loss caused by high latency and deadline violation, and increased energy consumption at devices, particularly due to repeated channel access requests. Collectively, these challenges constitute the so-called massive access problem [2], [3]. In general, channel access solutions addressing this problem in IIoT deployments must adapt to sporadic and correlated traffic [4], [5], require low signaling [5], [6], support decentralized decision-making [5], [7], and be scalable [5], [7]. ...
... where ξ(N ′ , A) = 1 represents a successful reception of the alarm message on at least one channel. Notice that (2) does not consider decoding errors as a potential cause of transmission failures. It only considers transmission failures resulting from medium access collision, similar to [4], [6]. ...
Efficient Random Access (RA) is critical for enabling reliable communication in Industrial Internet of Things (IIoT) networks. Herein, we propose a deep reinforcement learning-based distributed RA scheme, entitled Neural Network-Based Bandit (NNBB), for the IIoT alarm scenario. In such a scenario, devices may detect a common critical event, and the goal is to ensure the alarm information is delivered successfully from at least one device. The proposed NNBB scheme is implemented at each device, where it trains itself online and establishes implicit inter-device coordination to achieve the common goal. We devise a procedure for acquiring a valuable context for NNBB, which then uses a deep neural network to process this context and let devices determine their action. Each possible transmission pattern, i.e., transmit channel(s) allocation, constitutes a feasible action. Our simulation results show that as the number of devices in the network increases, so does the performance gain of the NNBB compared to the Multi-Armed Bandit (MAB) RA benchmark. For instance, NNBB experiences a 7% success rate drop when there are four channels and the number of devices increases from 10 to 60, while MAB faces a 25% drop.
... In IoTAC, there have been substantial advances on dealing with severe performance issues due to the large flows of IoT packets towards gateways from thousands of IoT devices, so that the resulting Massive Access Problem (MAP) has to be mitigated with novel traffic shaping techniques [81] as well as with techniques that can break the highly deterministic and massive aspects of many IoT traffic flows which create significant congestion at the receiving nodes [152]. ...
... The subsequent IoTAC project has lead to novel techniques for learning from user traffic and then testing for an attack as described in [181]. In IoTAC, there is also substantial work on dealing with severe performance issues due to the large flows of IoT packets towards gateways from thousands of IoT devices, so that the resulting Massive Access Problem (MAP) has to be mitigated with novel traffic shaping techniques [40], [41], [182], [183]. ...
This paper reviews research from several EU Projects that have addressed cybersecurity using techniques based on Machine Learning, including the security of Mobile Networks and the Internet of Things (IoT). These research projects have considered IoT Gateways and their design, security and performance, the security of digital health systems that are interconnected across Europe to provide health services to pople who travel through the EU, and related issues of the energy consumption and sustainability in Information and Communication Technologies (ICT) and their cybersecurity. The methods used in much of these research projects are based on Machine Learning both for attack detection and dynamic attack mitigation, as well as performance analysis and measurement techniques based on applied probability models.
This article summarizes briefly the contributions presented in this EuroCyberSecurity Workshop 2021 which is organized as part of the series of International Symposia on Computer and Information Sciences (ISCIS), with the support of the European Commission funded IoTAC Project, that was held on November and in NIce, France, and sponsored by the Institute of Teoretical and Applied Informatics of the Polish Academy of Sciences. It also summarizes some of the research contributions of several EU Projects including NEMESYS, GHOST, KONFIDO, SDK4ED and IoTAC, primarily with a cybersecurity and Machine Learning orientation. Thus subjects covered include the cybersecurity of Mobile Networks and of the Internet of Things (IoT), the design of IoT Gateways and their performance, the security of networked health systems that provide health services to individuals across the EU Member states, as well as the issues of energy consumption by ICT which are becoming increasingly important, including in the cybersecurity perspective, as we focus increasingly on climate change and the needed transition towards highly reduced emissions. Many of the techniques and results discussed in this article are based either on Machine Learning (ML) methods, or on methods for the performance modeling and optimization of networked and distributed computer systems.
