Smart City technology is an attempt to improve the quality of life of its citizens by providing promising smart solutions for multiple applications. These applications include healthcare monitoring, resource utilization, city resource management, and various public services. Internet of Things (IoT) enables smart city applications to collect data from various sensors and process it for providing numerous smart services to the end-users with improved performance. The diverse nature of IoT network requires the use of multiple types of sensors which produce a huge amount of data. This data is highly vulnerable to multiple service-oriented attacks; therefore, it must be protected during the communication of IoT nodes. This research work has focused on the identification and detection of malicious nodes causing service-oriented attacks in smart city applications and networks. The direct experience of communicating nodes and recommendations from neighboring nodes are collected to formulate a total trust score. The adaptive weights assigned to direct observations and indirect recommendations ensure the effectiveness of the Context-Based Trust Evaluation System Model (CTES) in detecting On–Off attacks. Moreover, context similarity measure calculations filter out those bad nodes which are posing a Sybil Attack. The proposed CTES has also been simulated on Contiki Cooja. The results also validate the effectiveness of CTES in detecting the bad behavior of malicious nodes.

智能城市技术是一种通过为多种应用提供有前途的智能解决方案来改善其居民生活质量的尝试。这些应用程序包括医疗保健监视，资源利用，城市资源管理和各种公共服务。物联网（IoT）使智能城市应用程序能够从各种传感器收集数据并对其进行处理，以为终端用户提供多种智能服务，从而提高性能。物联网网络的多样性要求使用多种类型的传感器，这些传感器会产生大量数据。这些数据极易受到多种面向服务的攻击的影响。因此，在物联网节点通信期间必须对其进行保护。这项研究工作集中于识别和检测在智能城市应用程序和网络中引起面向服务攻击的恶意节点。收集了通信节点的直接经验和来自相邻节点的建议，以制定总信任分数。分配给直接观察和间接建议的自适应权重可确保基于上下文的信任评估系统模型（CTES）在检测On-Off攻击方面的有效性。此外，上下文相似性度量计算可以过滤出构成Sybil攻击的不良节点。提议的CTES也已在Contiki Cooja上进行了模拟。结果还验证了CTES在检测恶意节点的不良行为方面的有效性。收集了通信节点的直接经验和来自相邻节点的建议，以制定总信任分数。分配给直接观察和间接建议的自适应权重可确保基于上下文的信任评估系统模型（CTES）在检测On-Off攻击方面的有效性。此外，上下文相似性度量计算可以过滤出构成Sybil攻击的不良节点。提议的CTES也已在Contiki Cooja上进行了模拟。结果还验证了CTES在检测恶意节点的不良行为方面的有效性。收集了通信节点的直接经验和来自相邻节点的建议，以制定总信任分数。分配给直接观察和间接建议的自适应权重可确保基于上下文的信任评估系统模型（CTES）在检测On-Off攻击方面的有效性。此外，上下文相似性度量计算可以过滤出构成Sybil攻击的不良节点。提议的CTES也已在Contiki Cooja上进行了模拟。结果还验证了CTES在检测恶意节点的不良行为方面的有效性。此外，上下文相似性度量计算可以过滤出构成Sybil攻击的不良节点。提议的CTES也已在Contiki Cooja上进行了模拟。结果还验证了CTES在检测恶意节点的不良行为方面的有效性。此外，上下文相似性度量计算可以过滤出构成Sybil攻击的不良节点。提议的CTES也已在Contiki Cooja上进行了模拟。结果还验证了CTES在检测恶意节点的不良行为方面的有效性。