Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454699
M. Alamgir, Brian Kelley
This study examines a cell-free massive MIMO architecture for unmanned aerial vehicles (UAVs), It evaluates aerial access points (APs) coverage, performance, and data rate of the aerial cell-free network. It proposes deploying an aerial cell-free massive MIMO architecture to mitigate the effects of path loss and interference in aerial cellular networks. The analysis includes a 2-dimensional multi-armed bandit (MAB) model for beam selection optimized with machine learning and using millimeter-wave technology to analyze an aerial cell-free network that connects a HAPS (CPU/data network) with ground vehicles through UAV-based APs. The multi-armed bandit model incorporates 3GPP blockage stochastics, water-filling power allocation, and optimization of multi-user capacity. The results include the aerial cell-free model's comprehensive geometric and radio link simulation analysis. The simulation outcomes demonstrate that the suggested cell-free network outperforms aerial cellular networks and NLOS terrestrial cell-free networks. Finally, we present a comparative study between our MAB model-based AI technique and a conventional non-AI technique, highlighting the significant performance improvements achieved by our approach.
本研究探讨了无人机（UAV）的无蜂窝大规模 MIMO 架构，评估了空中无蜂窝网络的空中接入点（AP）覆盖范围、性能和数据传输率。它建议部署空中无蜂窝大规模 MIMO 架构，以减轻空中蜂窝网络的路径损耗和干扰影响。分析包括利用机器学习和毫米波技术优化波束选择的二维多臂盗贼（MAB）模型，以分析通过基于无人机的接入点连接 HAPS（CPU/数据网络）和地面车辆的空中无蜂窝网络。多臂匪模型结合了 3GPP 阻塞随机性、充水功率分配和多用户容量优化。结果包括空中无蜂窝模型的综合几何和无线电链路仿真分析。仿真结果表明，建议的无蜂窝网络优于空中蜂窝网络和 NLOS 陆地无蜂窝网络。最后，我们介绍了基于 MAB 模型的人工智能技术与传统非人工智能技术之间的比较研究，强调了我们的方法所取得的显著性能改进。
{"title":"On the Analysis of AI-Optimized Aerial Cell-Free Massive MIMO","authors":"M. Alamgir, Brian Kelley","doi":"10.1109/CCNC51664.2024.10454699","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454699","url":null,"abstract":"This study examines a cell-free massive MIMO architecture for unmanned aerial vehicles (UAVs), It evaluates aerial access points (APs) coverage, performance, and data rate of the aerial cell-free network. It proposes deploying an aerial cell-free massive MIMO architecture to mitigate the effects of path loss and interference in aerial cellular networks. The analysis includes a 2-dimensional multi-armed bandit (MAB) model for beam selection optimized with machine learning and using millimeter-wave technology to analyze an aerial cell-free network that connects a HAPS (CPU/data network) with ground vehicles through UAV-based APs. The multi-armed bandit model incorporates 3GPP blockage stochastics, water-filling power allocation, and optimization of multi-user capacity. The results include the aerial cell-free model's comprehensive geometric and radio link simulation analysis. The simulation outcomes demonstrate that the suggested cell-free network outperforms aerial cellular networks and NLOS terrestrial cell-free networks. Finally, we present a comparative study between our MAB model-based AI technique and a conventional non-AI technique, highlighting the significant performance improvements achieved by our approach.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"70 11","pages":"784-791"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454785
Alexander Jung, Helge Parzyjegla, Peter Danielis
In the modern world, accurate crowd counting is integral to a multitude of applications, including urban planning, transportation management, and crowd control. The advent of opportunistic communication networks, which enable devices to sporadically exchange data in a decentralized fashion, has introduced a new set of challenges in crowd estimation. This paper delves into two opportunistic people counting protocols: UrbanCount and HeartBeatCount. UrbanCount, while a robust protocol in its own right, comes with certain limitations that hinder its real-world applicability. In response to these limitations, this paper introduces refinements to UrbanCount, making it more practical and effective. Additionally, a novel protocol called HeartBeatCount is presented, which significantly enhances crowd size estimation accuracy, particularly in sparse scenarios. Through an evaluation, we compare the performance of these protocols and conclude that HeartBeatCount offers a more resilient solution for opportunistic people counting in various real-world scenarios.
{"title":"Opportunistic Protocols for People Counting in Dynamic Networks","authors":"Alexander Jung, Helge Parzyjegla, Peter Danielis","doi":"10.1109/CCNC51664.2024.10454785","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454785","url":null,"abstract":"In the modern world, accurate crowd counting is integral to a multitude of applications, including urban planning, transportation management, and crowd control. The advent of opportunistic communication networks, which enable devices to sporadically exchange data in a decentralized fashion, has introduced a new set of challenges in crowd estimation. This paper delves into two opportunistic people counting protocols: UrbanCount and HeartBeatCount. UrbanCount, while a robust protocol in its own right, comes with certain limitations that hinder its real-world applicability. In response to these limitations, this paper introduces refinements to UrbanCount, making it more practical and effective. Additionally, a novel protocol called HeartBeatCount is presented, which significantly enhances crowd size estimation accuracy, particularly in sparse scenarios. Through an evaluation, we compare the performance of these protocols and conclude that HeartBeatCount offers a more resilient solution for opportunistic people counting in various real-world scenarios.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"66 9","pages":"198-201"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In advancing society, large-capacity and high-speed communication network, to handle rich contents like ultra-high-definition video and large-capacity sensing information, is becoming important. Accomplishing these demands needs an ultrawide bandwidth wireless Local Area Network (LAN). Improvements in wireless transmission speeds are expected with the development of ultra-high-speed wireless technology such as terahertz (THz) communication. However, the rapid growth of ultra-high-speed wireless network technology places a considerable strain on the backhaul network. Therefore, improvements in wired network technology are indispensable to achieve higher speeds. We investigated RDMA technology used in data centers to speed up in THz wireless LAN. This paper presents the construction of a backhaul system to connect a network coordinator and interconnected access points. It also reports evaluation results of the proposed system, including a comparative analysis concerning RoCE, TCP, and UDP. Furthermore, the effect of switching processing on the overall throughput.
{"title":"Evaluation of RoCE Protocol in Backhaul Systems for Ultra-High-Speed THz Wireless LAN","authors":"Norimasa Yafune, Kazuto Yano, Keiichiro Mori, Toshikazu Sakano","doi":"10.1109/CCNC51664.2024.10454796","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454796","url":null,"abstract":"In advancing society, large-capacity and high-speed communication network, to handle rich contents like ultra-high-definition video and large-capacity sensing information, is becoming important. Accomplishing these demands needs an ultrawide bandwidth wireless Local Area Network (LAN). Improvements in wireless transmission speeds are expected with the development of ultra-high-speed wireless technology such as terahertz (THz) communication. However, the rapid growth of ultra-high-speed wireless network technology places a considerable strain on the backhaul network. Therefore, improvements in wired network technology are indispensable to achieve higher speeds. We investigated RDMA technology used in data centers to speed up in THz wireless LAN. This paper presents the construction of a backhaul system to connect a network coordinator and interconnected access points. It also reports evaluation results of the proposed system, including a comparative analysis concerning RoCE, TCP, and UDP. Furthermore, the effect of switching processing on the overall throughput.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"26 1","pages":"811-814"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Low-delay networking and edge computing will enable mission-critical applications to be delivered over wide-area networks. We consider this trend to be the realization that all users can share an application space without feeling any distance difference. We propose a distributed processing scheme that keeps the order of event occurrence regardless of the distance between users and an application server. The proposed scheme can be applied to both optimistic synchronization algorithms (OSA) and conservative synchronization algorithms (CSA). In the proposed scheme, arrival events with a delay within a predefined set time (correction time) are sorted in order of occurrence before application processing. We formulate the proposed scheme as an integer linear programming (ILP) problem. The objective function of ILP consists of the number of users excluded from the delay quality, the amount of memory consumed for a rollback in OSA, and the maximum end-to-end delay. The three parts of the objective function are set weight and the sum of parts with weight is minimized. We evaluate the proposed scheme for 1000 users distributed in two types of network models. Numerical results indicate that the proposed scheme reduces memory consumption compared to that of the conventional OSA scheme. The proposed scheme works as CSA in which all events are sorted in the occurrence order if the correction time is set above the delay for the slowest event to arrive at the server.
低延迟网络和边缘计算将使关键任务应用能够通过广域网交付。我们认为这一趋势是实现所有用户都能共享一个应用空间，而不会感觉到任何距离上的差异。我们提出了一种分布式处理方案，无论用户与应用服务器之间的距离有多远，都能保持事件发生的顺序。我们提出的方案既适用于乐观同步算法（OSA），也适用于保守同步算法（CSA）。在所提出的方案中，延迟时间在预定义时间（校正时间）内的到达事件会在应用处理前按发生顺序排序。我们将拟议方案表述为一个整数线性规划（ILP）问题。ILP 的目标函数包括从延迟质量中排除的用户数量、OSA 回滚所消耗的内存量和最大端到端延迟。目标函数的三个部分都设定了权重，各部分权重之和最小。我们以分布在两种网络模型中的 1000 个用户为对象，对所提出的方案进行了评估。数值结果表明，与传统的 OSA 方案相比，拟议方案减少了内存消耗。如果校正时间设置为高于最慢事件到达服务器的延迟时间，则提议的方案就会像 CSA 那样工作，所有事件都会按发生顺序排序。
{"title":"A Distributed Processing Communication Scheme for Real-Time Applications over Wide-Area Networks","authors":"Sanetora Hiragi, Bijoy Chand Chatterjee, Eiji Oki, Akio Kawabata","doi":"10.1109/CCNC51664.2024.10454684","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454684","url":null,"abstract":"Low-delay networking and edge computing will enable mission-critical applications to be delivered over wide-area networks. We consider this trend to be the realization that all users can share an application space without feeling any distance difference. We propose a distributed processing scheme that keeps the order of event occurrence regardless of the distance between users and an application server. The proposed scheme can be applied to both optimistic synchronization algorithms (OSA) and conservative synchronization algorithms (CSA). In the proposed scheme, arrival events with a delay within a predefined set time (correction time) are sorted in order of occurrence before application processing. We formulate the proposed scheme as an integer linear programming (ILP) problem. The objective function of ILP consists of the number of users excluded from the delay quality, the amount of memory consumed for a rollback in OSA, and the maximum end-to-end delay. The three parts of the objective function are set weight and the sum of parts with weight is minimized. We evaluate the proposed scheme for 1000 users distributed in two types of network models. Numerical results indicate that the proposed scheme reduces memory consumption compared to that of the conventional OSA scheme. The proposed scheme works as CSA in which all events are sorted in the occurrence order if the correction time is set above the delay for the slowest event to arrive at the server.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"108 5","pages":"25-30"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454839
Keita Fukushima, Keiichi Mizutani, H. Harada
Toward 6G, cell-free networks (CFN) are attracting attention as a solution to the problem of poor communication quality at the cell edge. In CFN, many access points are densely deployed and cooperatively operated as distributed MIMO systems. In uplink communication in CFN, transmit power control (TPC) is required to mitigate interference and ensure fairness between users. In this paper, we propose an open-loop TPC algorithm for CFN and evaluate its performance by computer simulation. As a result, an improvement of 55.0% in the fifth percentile spectral efficiency is achieved compared to the case without TPC while maintaining a higher average spectral efficiency.
{"title":"A Study on Open-Loop Transmit Power Control for Scalable Cell-Free Networks","authors":"Keita Fukushima, Keiichi Mizutani, H. Harada","doi":"10.1109/CCNC51664.2024.10454839","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454839","url":null,"abstract":"Toward 6G, cell-free networks (CFN) are attracting attention as a solution to the problem of poor communication quality at the cell edge. In CFN, many access points are densely deployed and cooperatively operated as distributed MIMO systems. In uplink communication in CFN, transmit power control (TPC) is required to mitigate interference and ensure fairness between users. In this paper, we propose an open-loop TPC algorithm for CFN and evaluate its performance by computer simulation. As a result, an improvement of 55.0% in the fifth percentile spectral efficiency is achieved compared to the case without TPC while maintaining a higher average spectral efficiency.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"87 2","pages":"1074-1075"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454698
T. Vrind, Chandar Kumar, Debabrata Das
In the 6G wireless network, there may be a communication architecture with three levels of systems: user equipment (UE), non-terrestrial aerial low altitude platform (LAP), and terrestrial base station with mobile edge computing (MEC). Co-inference is the intelligent sharing of the multiple computing layers in the AI/ML model amongst the UE, LAP, and MEC. Computing, storage, and power shared between the above systems for co-inference will bring several system-level advantages. Furthermore, it optimizes the required data traffic bandwidth, energy consumption, and end-to-end latency. The available literature has analyzed the optimal split point of the AI/ML model between UE and MEC (one wireless link). However, to the best of our knowledge, there is no study on the AI/ML split model in the case of UE, LAP, and MEC architectures with two wireless links (UE to LAP and LAP to MEC). In this paper, for the first time, we propose a novel device-edge co-inference with a LAP-based aerial cell having computing power. We present a novel Aerial Cell-Assisted Device-Edge co-inference ModEl (ACADEME) algorithm that optimally assigns layers to compute to UE, LAP, and MEC according to two wireless link characteristics to minimize power consumption and latency of inference. Through mathematical modelling and simulations, we show that the proposed coinference substantially reduces latency, i.e., by 47% through the selection of the two optimal split points of the AI/ML model, one each at the UE and the LAP-based aerial cell, respectively.
在 6G 无线网络中，通信架构可能包含三个层次的系统：用户设备（UE）、非地面空中低空平台（LAP）和带有移动边缘计算（MEC）的地面基站。协同干涉是指 UE、LAP 和 MEC 之间智能共享 AI/ML 模型中的多个计算层。上述系统之间共享计算、存储和电源以进行协同干涉将带来多个系统级优势。此外，它还能优化所需的数据流量带宽、能耗和端到端延迟。现有文献分析了 AI/ML 模型在 UE 和 MEC（一条无线链路）之间的最佳分割点。然而，据我们所知，目前还没有关于 UE、LAP 和 MEC 架构中两个无线链路（UE 至 LAP 和 LAP 至 MEC）的 AI/ML 分离模型的研究。在本文中，我们首次提出了一种新型的设备边缘协同干扰，它基于具有计算能力的 LAP 空中小区。我们提出了一种新型的空中小区辅助设备边缘协同干扰模式（ACADEME）算法，该算法可根据两种无线链路特性为 UE、LAP 和 MEC 分配最佳计算层，以最大限度地降低功耗和推理延迟。通过数学建模和仿真，我们发现所提出的协同推理通过选择 AI/ML 模型的两个最佳分割点（分别位于 UE 和基于 LAP 的空中小区），大大减少了延迟，即减少了 47%。
{"title":"ACADEME: Aerial Cell-Assisted Device-Edge coinference ModEl in 6G Wireless Network","authors":"T. Vrind, Chandar Kumar, Debabrata Das","doi":"10.1109/CCNC51664.2024.10454698","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454698","url":null,"abstract":"In the 6G wireless network, there may be a communication architecture with three levels of systems: user equipment (UE), non-terrestrial aerial low altitude platform (LAP), and terrestrial base station with mobile edge computing (MEC). Co-inference is the intelligent sharing of the multiple computing layers in the AI/ML model amongst the UE, LAP, and MEC. Computing, storage, and power shared between the above systems for co-inference will bring several system-level advantages. Furthermore, it optimizes the required data traffic bandwidth, energy consumption, and end-to-end latency. The available literature has analyzed the optimal split point of the AI/ML model between UE and MEC (one wireless link). However, to the best of our knowledge, there is no study on the AI/ML split model in the case of UE, LAP, and MEC architectures with two wireless links (UE to LAP and LAP to MEC). In this paper, for the first time, we propose a novel device-edge co-inference with a LAP-based aerial cell having computing power. We present a novel Aerial Cell-Assisted Device-Edge co-inference ModEl (ACADEME) algorithm that optimally assigns layers to compute to UE, LAP, and MEC according to two wireless link characteristics to minimize power consumption and latency of inference. Through mathematical modelling and simulations, we show that the proposed coinference substantially reduces latency, i.e., by 47% through the selection of the two optimal split points of the AI/ML model, one each at the UE and the LAP-based aerial cell, respectively.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"70 3","pages":"1006-1009"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454841
Alex Howe, Dale Peasley, Mauricio Papa
This paper evaluates the use of graph neural network (GNN) based autoencoders for detecting network intrusions or anomalous traffic in Operational Technology (OT) networks. Traditional intrusion detection methods often struggle to capture the complex relationships and interdependencies found in OT network communications. These spatial relationships can provide information vital for identifying harder to detect attacks (i.e. Advanced Persistent Threats). GNNs are a machine learning technique which operate on graph-structured data and can be used to identify underlying patterns and relationships between the nodes. Graph autoencoders (GAEs) are an unsupervised GNN-based learning technique that incorporates an encoder-decoder architecture and can be used for anomaly detection in graph structured data. This work evaluates the use of graph autoencoders for detecting anomalous edges (extracted from packets) in OT network data. Additionally, we introduce a method for encoding raw network traffic into discrete temporal graphs which can be used to apply GAEs for real-time intrusion detection. The proposed network traffic encoding scheme incorporates multi-dimensional edge attributes in order to capture information for determining the relevance of a given network packet. The approach is evaluated using two OT network datasets each containing labeled examples of commonly encountered malicious attack traffic. Results are compared against baseline anomaly detection methods including K-Nearest Neighbors, Deep Autoencoders, and Isolation Forest. The proposed graph autoencoder outperforms the baseline cases in terms of detection accuracy achieving a 31.05% and 8.64% improvement in F1 scores over the baseline models on the two OT network datasets.
本文评估了基于图神经网络（GNN）的自动编码器在检测操作技术（OT）网络中的网络入侵或异常流量方面的应用。传统的入侵检测方法往往难以捕捉到 OT 网络通信中的复杂关系和相互依存关系。这些空间关系可为识别难以检测的攻击（即高级持续性威胁）提供重要信息。GNN 是一种机器学习技术，可在图结构数据上运行，并可用于识别节点之间的基本模式和关系。图自动编码器（GAE）是一种基于 GNN 的无监督学习技术，它采用编码器-解码器架构，可用于图结构数据的异常检测。这项研究评估了如何使用图自编码器检测 OT 网络数据中的异常边缘（从数据包中提取）。此外，我们还介绍了一种将原始网络流量编码为离散时间图的方法，该方法可用于应用 GAE 进行实时入侵检测。所提出的网络流量编码方案包含多维边缘属性，以便捕捉用于确定给定网络数据包相关性的信息。我们使用两个 OT 网络数据集对该方法进行了评估，每个数据集都包含常见恶意攻击流量的标记示例。结果与基准异常检测方法（包括 K-近邻、深度自动编码器和隔离林）进行了比较。在两个 OT 网络数据集上，拟议的图自动编码器在检测准确性方面优于基线案例，F1 分数比基线模型分别提高了 31.05% 和 8.64%。
{"title":"Graph Autoencoders for Detecting Anomalous Intrusions in OT Networks Through Dynamic Link Detection","authors":"Alex Howe, Dale Peasley, Mauricio Papa","doi":"10.1109/CCNC51664.2024.10454841","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454841","url":null,"abstract":"This paper evaluates the use of graph neural network (GNN) based autoencoders for detecting network intrusions or anomalous traffic in Operational Technology (OT) networks. Traditional intrusion detection methods often struggle to capture the complex relationships and interdependencies found in OT network communications. These spatial relationships can provide information vital for identifying harder to detect attacks (i.e. Advanced Persistent Threats). GNNs are a machine learning technique which operate on graph-structured data and can be used to identify underlying patterns and relationships between the nodes. Graph autoencoders (GAEs) are an unsupervised GNN-based learning technique that incorporates an encoder-decoder architecture and can be used for anomaly detection in graph structured data. This work evaluates the use of graph autoencoders for detecting anomalous edges (extracted from packets) in OT network data. Additionally, we introduce a method for encoding raw network traffic into discrete temporal graphs which can be used to apply GAEs for real-time intrusion detection. The proposed network traffic encoding scheme incorporates multi-dimensional edge attributes in order to capture information for determining the relevance of a given network packet. The approach is evaluated using two OT network datasets each containing labeled examples of commonly encountered malicious attack traffic. Results are compared against baseline anomaly detection methods including K-Nearest Neighbors, Deep Autoencoders, and Isolation Forest. The proposed graph autoencoder outperforms the baseline cases in terms of detection accuracy achieving a 31.05% and 8.64% improvement in F1 scores over the baseline models on the two OT network datasets.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"2 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454653
Achim Schade, Vu Nguyen, Cansu Gencoglu, Giang T. Nguyen, F. Fitzek
Human-robot interaction is crucial in various industries and domains, such as manufacturing, healthcare, and entertainment. Natural and intuitive interactions between humans and robots are crucial. Legacy controllers were designed for two-dimensional visual display and, therefore, suboptimal for interaction in three-dimensional space. Hand gesture recognition with camera-based systems is often hindered by visual obstruction. We demonstrate a hand gesture system leveraging data gloves with inertial measurement units (IMU). This demonstration focuses on gesture recognition quality, enhancing robustness and responsiveness. Audiences can observe and directly participate using the data glove to maneuver a robotic dog remotely in real-time.
{"title":"Intuitive Robot Control with Data Gloves for Industrial Use Cases","authors":"Achim Schade, Vu Nguyen, Cansu Gencoglu, Giang T. Nguyen, F. Fitzek","doi":"10.1109/CCNC51664.2024.10454653","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454653","url":null,"abstract":"Human-robot interaction is crucial in various industries and domains, such as manufacturing, healthcare, and entertainment. Natural and intuitive interactions between humans and robots are crucial. Legacy controllers were designed for two-dimensional visual display and, therefore, suboptimal for interaction in three-dimensional space. Hand gesture recognition with camera-based systems is often hindered by visual obstruction. We demonstrate a hand gesture system leveraging data gloves with inertial measurement units (IMU). This demonstration focuses on gesture recognition quality, enhancing robustness and responsiveness. Audiences can observe and directly participate using the data glove to maneuver a robotic dog remotely in real-time.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"95 11","pages":"1114-1115"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454813
A. Siddiqua, Siming Liu, Razib Iqbal, Fahim Ahmed Irfan, Logan Ross, Brian Zweerink
Information sharing among agents to jointly solve problems is challenging for multi-agent reinforcement learning algorithms (MARL) in smart environments. In this paper, we present a novel information sharing approach for MARL, which introduces a Team Information Matrix (TIM) that integrates scenario-independent spatial and environmental information combined with the agent's local observations, augmenting both individual agent's performance and global awareness during the MARL learning. To evaluate this approach, we conducted experiments on three multi-agent scenarios of varying difficulty levels implemented in Unity ML-Agents Toolkit. Experimental results show that the agents utilizing our TIM-Shared variation outperformed those using decentralized MARL and achieved comparable performance to agents employing centralized MARL.
{"title":"TIM-MARL: Information Sharing for Multi-Agent Reinforcement Learning in Smart Environments","authors":"A. Siddiqua, Siming Liu, Razib Iqbal, Fahim Ahmed Irfan, Logan Ross, Brian Zweerink","doi":"10.1109/CCNC51664.2024.10454813","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454813","url":null,"abstract":"Information sharing among agents to jointly solve problems is challenging for multi-agent reinforcement learning algorithms (MARL) in smart environments. In this paper, we present a novel information sharing approach for MARL, which introduces a Team Information Matrix (TIM) that integrates scenario-independent spatial and environmental information combined with the agent's local observations, augmenting both individual agent's performance and global awareness during the MARL learning. To evaluate this approach, we conducted experiments on three multi-agent scenarios of varying difficulty levels implemented in Unity ML-Agents Toolkit. Experimental results show that the agents utilizing our TIM-Shared variation outperformed those using decentralized MARL and achieved comparable performance to agents employing centralized MARL.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"107 4","pages":"1044-1045"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-06DOI: 10.1109/CCNC51664.2024.10454872
Wenxin Chen, Yingfei Dong, Zhenhai Duan
As many mobile devices use Global Navigation Satellite Systems (GNSSs) to determine their locations for control, compromising such systems can result in serious consequences, as shown by existing GPS spoofing attacks. However, most such spoofing attacks focus on the effect of a single spoofer attacking a single receiver. In this paper, we investigate the impacts of a single spoofer on multiple receivers, motivated by research on attacking drone swarms. Our analysis independently shows that, using a single spoofer, multiple receivers at different locations in a spoofing area will see the same location reading. We consider the base case of spoofing four satellites and also the generic case when more satellites are involved in the spoofing attack. More importantly, we conduct real-world experiments to validate our analysis and demonstrate the potential threats to many practical applications. We use off-the-shelf SDR cards for spoofing and consumer GPS receivers for obtaining spoofed location readings. While this method can enable various attacks on mobile devices depending on GPS, it is also applicable to all existing GNSSs, because they use similar principles to determine locations.
{"title":"Impacts of a Single GPS Spoofer on Multiple Receivers: Formal Analysis and Experimental Evaluation","authors":"Wenxin Chen, Yingfei Dong, Zhenhai Duan","doi":"10.1109/CCNC51664.2024.10454872","DOIUrl":"https://doi.org/10.1109/CCNC51664.2024.10454872","url":null,"abstract":"As many mobile devices use Global Navigation Satellite Systems (GNSSs) to determine their locations for control, compromising such systems can result in serious consequences, as shown by existing GPS spoofing attacks. However, most such spoofing attacks focus on the effect of a single spoofer attacking a single receiver. In this paper, we investigate the impacts of a single spoofer on multiple receivers, motivated by research on attacking drone swarms. Our analysis independently shows that, using a single spoofer, multiple receivers at different locations in a spoofing area will see the same location reading. We consider the base case of spoofing four satellites and also the generic case when more satellites are involved in the spoofing attack. More importantly, we conduct real-world experiments to validate our analysis and demonstrate the potential threats to many practical applications. We use off-the-shelf SDR cards for spoofing and consumer GPS receivers for obtaining spoofed location readings. While this method can enable various attacks on mobile devices depending on GPS, it is also applicable to all existing GNSSs, because they use similar principles to determine locations.","PeriodicalId":518411,"journal":{"name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","volume":"106 2","pages":"127-134"},"PeriodicalIF":0.0,"publicationDate":"2024-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：