5G-based mobile ad hoc networks with cloud are a new paradigm that combines several real-world applications. Routing and security are current issues in MANETs. Security is highly important in MANET and cloud environments for preventing harmful attacks. Therefore, a trusted environment is required for a MANET with cloud-based 5G communications. In this paper, we propose a new framework called trust-aware intrusion detection and prevention system (TA-IDPS) for protecting the network from adversaries. TA-IDPS consists of a MANET, a cloudlet, and a cloud service layer. Initially, we register and authenticate mobile nodes using an ultra-lightweight symmetric cryptographic technique, which is highly suitable for resource-constrained environments. In MANETs, high energy consumption, scalability, and authentication are important issues, which are addressed by the proposed moth flame optimization algorithm. If the cluster head (CH) receives data packets from a source node, they are classified as normal, malicious, and suspicious using a deep belief network. Intra-cluster routing is implemented by an adaptive Bayesian estimator using next-best forwarder selection. In the cloudlet layer, cloudlets are used to aggregate packets from the CH and verify their legitimacy so that they can be forwarded to the cloud service layer. Each cloudlet is provided with a peek monitor for classifying suspicious packets as malicious and normal using Awads information entropy. Experiments are conducted using NS3.26. The performance of the proposed TA-IDPS and previous methods is analyzed using widely used metrics. The evaluation results demonstrated that the proposed TA-IDPS system outperformed the previous methods in terms of all metrics.

带有云的基于 5G 的移动自组织网络是一种新范式，它结合了多个现实世界的应用程序。路由和安全是 MANET 中的当前问题。在 MANET 和云环境中，安全性对于防止有害攻击非常重要。因此，具有基于云的 5G 通信的 MANET 需要可信环境。在本文中，我们提出了一种称为信任感知入侵检测和预防系统 (TA-IDPS) 的新框架，用于保护网络免受攻击者的侵害。TA-IDPS 由 MANET、小云和云服务层组成。最初，我们使用非常适合资源受限环境的超轻量级对称加密技术注册和验证移动节点。在 MANET 中，高能耗、可扩展性和身份验证是重要的问题，提出的飞蛾火焰优化算法解决了这些问题。如果簇头（CH）从源节点接收数据包，则使用深度信念网络将它们分类为正常、恶意和可疑。集群内路由由自适应贝叶斯估计器使用次佳转发器选择实现。在小云层，小云用于聚合来自CH的数据包并验证其合法性，以便将它们转发到云服务层。每个小云都配备了一个窥视监视器，用于使用 Awads 信息熵将可疑数据包分类为恶意和正常数据包。使用 NS3.26 进行实验。使用广泛使用的指标分析了所提出的 TA-IDPS 和以前方法的性能。