Cloud Computing (CC) is an innovative worldview technique that allows for the registration of resources. Some examples of computing resources are an organization, stockpiling, applications, and administrations when there is an interesting perspective. In CC, the assets are shared by Cloud customers. A registered framework is given by the cloud which is an advanced stage on which clients can build up their applications. Having a limited service, the consumers of the cloud can gain resources from anywhere irrespective of time. One of the topical issues is Edge and Fog computing along with the cloud security that is associated with the processing paradigm, data storage, and managing. When attacks occur on the advancement of fog computing, IoT Cloud figuring, ineradicable and appalling impacts transpire. Subsequently, numerous security frameworks and models have been proposed and executed for security in Fog computing. The proposed model addresses the privacy concerns as many networks are involved, and there are many fog nodes that each end-user is accessible to those nodes. This is due to more sensitive information that is transferred from end-users to the fog nodes. The proposed model uses multi-layered intermittent neural organizations intended to be executed for Fog computing figuring the security that is exceptionally near the end-clients and IoT gadgets. The proposed model utilizes a reasonable adaptation of the difficult dataset such as the NSL-KDD dataset. The performance of the proposed model was evaluated using a range of existing models, features. The research findings and replications are used to demonstrate the robustness and stability of the proposed model in comparison with other types of execution measurements.

云计算（CC）是一种创新的世界观技术，可用于注册资源。当有有趣的观点时，组织，存储，应用程序和管理是计算资源的一些示例。在CC中，资产由Cloud客户共享。云提供了已注册的框架，这是客户端可以构建其应用程序的高级阶段。由于服务有限，云用户可以从任何地方获取资源，而无需考虑时间。主题问题之一是Edge和Fog计算以及与处理范例，数据存储和管理相关的云安全性。当随着雾计算的发展而发生攻击时，物联网云计算，无法消除和令人震惊的影响就将席卷而来。随后，为了雾计算中的安全性，已经提出并执行了许多安全性框架和模型。提议的模型解决了涉及许多网络的隐私问题，并且每个终端用户都可以访问这些节点的许多雾节点。这是由于从最终用户传输到雾节点的信息更加敏感。拟议的模型使用旨在为Fog计算执行的多层间歇性神经组织，从而证明了在最终客户端和IoT小工具附近的安全性。所提出的模型利用了困难数据集（例如NSL-KDD数据集）的合理改编。使用一系列现有模型，功能对所提出模型的性能进行了评估。