(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 12, No. 9, 2021 456 | Page www.ijacsa.thesai.org Detection of Intruder in Cloud Computing Environment using Swarm Inspired based Neural Network Nishika 1 Ph.D. Research Scholar UIET, Maharshi Dayanand University Rohtak, Haryana, India Kamna Solanki 2 Assistant Professor UIET, Maharshi Dayanand University Rohtak, Haryana, India Sandeep Dalal 3 Assistant Professor DCSA, Maharshi Dayanand University, Rohtak, Haryana, India Abstract—Cloud computing services offered a resource pool with a wide range of storage for large amounts of data. Cloud services are generally used as a demand-driven private or open data forum, and the increase in use has led to security concerns. Therefore, it is necessary to design an accurate Intrusion Detection System (IDS) to identify the suspected node in the cloud computing environment. This is possible by monitoring network traffic so that the quality of service and performance of the system can be maintained. Several researchers have worked on designing valid IDS with the help of a machine learning approach. A single classification algorithm seems to be impossible to detect intruders with high accuracy. Therefore, a hybrid approach is presented. This approach is a combination of Cuckoo Search. CS as an optimization algorithm and Feed Forward Back Propagation Neural Network (FFBPNN) as a multi-class classification approach. The user's request to access cloud data is collected and essential features are selected using CS as an optimization approach. The selected features are used to train FFBPNN with reduced training time and complexity. The experimental analysis has been performed in terms of precision, recall, F-measure, and accuracy. The evaluated value for parameters i.e., precision (85.5%), recall (86.4%), F-measure (85.9%), and accuracy (86.22%) are observed. At last, the parameters are also compared with the existing approach. Keywords—Cloud computing; intrusion detection system; cuckoo search; feed forward back propagation neural network (FFBPNN) I. INTRODUCTION In this modern era, cloud computing has transformed the IT world with rapidly evolving and extensively accepted computing-based systems. The attractive features of Cloud Computing continue to increase integration in many sectors, such as governments, private, including industry, education, and entertainment [1]. According to the National Institute of Standards and Technology (NIST), cloud computing is defined as the computational model, which delivered services on-demand [2]. Cloud Computing provides a variety of applications and services to customers or users on the Internet. Services are provided remotely from various servers or the cloud, which is far from the users. Cloud Computing allows the user to use different software types in the cloud without installing the user system. Currently, there is a growing demand for clouds due to these devices, which leads to the need to take security measures because, with the increase in the demand, more security is required against threats [3]. There are already many businesses that use cloud computing services with their attractive features such as on-demand services, extensive network access, fast flexibility, and, finally, measurable services. Such features will allow users to focus on business processes while managing computing resources through a cloud service provider (CSP). Using cloud features, the operating costs are reduced by ensuring the compatibility and availability of different computing sources, simplifying device installation, and process with software and hardware updates [4]. There are several service provider models such as the private model, public model, community model, and hybrid model in the market. The cloud model that offers services to their individual or specific users is termed a public cloud. By using this cloud model, the services are delivered to the general public, managed, and controlled by private or government, or semi-government agencies. The private cloud infrastructure is extensive and provided for use by a single organization. The community cloud model is also presented to be used by a defined community. Here, community means a group of organizations with similar interests. A new cloud infrastructure is a hybrid cloud that consists of the right combination of different infrastructures, which can be individual (private), public, or community [5]. The organization, as well as the security of these cloud models, needs to be improved so that the stored data by many cloud users remain safe. This is possible through the utilization of the Intrusion Detection System (IDS). A suspicious entry in the network is known as an intrusion [6]. Therefore, it is necessary to design efficient IDS that can protect the stored data against suspicious users. IDS can be divided into two types, one is Host-based IDS (H-IDS), and the other is Network-based IDS (N-IDS) [7]. The first H-IDS intrusion detection program was developed using the original target system as the primary host computer, where some external interactions are often absent. HIDS will operate based on information collected using a personal computer system. It monitors all incoming and outgoing packets on the computer system and notifies users or the administrator if it is observed that there is a suspicious activity. This can be used commonly to protect personal information, which is valuable for several server-based systems [8].