BEAST: Behavior as a Service for Trust management in IoT devices
BEAST: Behavior as a Service for Trust management in IoT devices
复制标题
BEAST：物联网设备中信任管理的行为即服务
DOI：
10.1016/j.future.2023.02.003
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Skjellum, Anthony
中科院分区：
文献类型：
--
作者：
Huber, Brennan;Kandah, Farah;Skjellum, Anthony
随着互联网融入人类生活的方方面面，物联网（IoT）的安全也变得越来越重要。物联网设备正在成为各种智慧城市应用的主要数据源，其中关键决策基于这些收集的数据。如果恶意行为者控制和/或篡改正在传输的数据，整个智慧城市的完整性将受到损害。然而，通过监控物联网设备的行为，可以检测和隔离异常情况，以避免对决策产生任何负面影响。这种行为监控过程将补充传统的信任管理方法，因为可以计算更准确的信任值，而无需依赖多数共识。在这项工作中，我们提出了一种用于信任管理的行为即服务（BEAST），它实现了基于深度学习的行为模型，以准确地对系统中物联网设备的交互进行分类。通过Elo评级系统的实施，这些分类将呈现为每个设备的行为向量，这动态地反映了每个设备对系统的信任度。这项工作对我们的方法和威胁模型进行了分析。通过模拟，呈现了一个真实世界的用例，展示了基于物联网的设备之间的交互。我们的结果表明，我们的 BEAST 模型能够动态评估每个物联网设备的信任，以及捕获和减轻针对系统信任的多种威胁。
As the internet becomes intertwined into every aspect of human life, the security of the Internet of Things (IoT) is also becoming increasingly critical. IoT devices are becoming the primary data source for a variety of smart-city applications, where critical decisions are based on this collected data. If malicious actors gain control of and/or tamper with the data being transmitted, the integrity of an entire smart city will be compromised. However, through monitoring IoT devices’ behavior, anomalies can be detected and isolated to avoid any negative impact on decision-making. This behavioral monitoring process will complement traditional trust management approaches, since more accurate trust values can be calculated without the need to rely on a majority consensus. In this work, we present a BEhavior-As-a-Service for Trust management (BEAST) that implements a deep learning-based behavioral model to accurately classify IoT devices’ interactions in the system. Through the implementation of the Elo rating system, these classifications will be presented as a vector of behaviors per device, which dynamically reflects each device’s trust in the system. This work presents an analysis of our methodology as well as a threat model. Using simulations, a real-world use case is presented showing the interactions between IoT-based devices. Our results show that our BEAST model is able to dynamically evaluate each IoT device’s trust, as well as capture and mitigate multiple threats targeting the trust in the system.
登录
查看更多内容
使用多样性和无监督学习识别多跳物联网网络中的恶意节点
DOI：
--
发表时间：
2018
期刊：
2018 IEEE International Conference on Communications (ICC)
影响因子：
--
作者：
Xin Liu;Mai Abdelhakim;P. Krishnamurthy;D. Tipper
通讯作者：
D. Tipper
影响因子：
10.6
作者：
Reising, Donald;Cancelleri, Joseph;Skjellum, Anthony
通讯作者：
Skjellum, Anthony
恶意物联网：关联主动和被动测量以推断和表征互联网规模的未经请求的物联网设备
影响因子：
11.2
作者：
Shaikh, Farooq;Bou-Harb, Elias;Neshenko, Nataliia;Wright, Andrea P.;Ghani, Nasir
通讯作者：
Ghani, Nasir
多智能体传感器融合互联
DOI：
--
发表时间：
2019
期刊：
International Conference on Intelligent Transportation Systems
影响因子：
--
作者：
Suryansh Saxena;Isaac K. Isukapati;Stephen F. Smith;J. Dolan
通讯作者：
J. Dolan