Detection of DoS Attack using Pearson Correlation Coefficients with Bi-LSTM and LZW Compression

Access to information, software, and applications through the Internet has been made possible through cloud computing technologies. An individual consumer with a computer and an internet connection can access the applications and request the necessary amenities or resources from any location through cloud networks. With these developments in cloud networks, dangers are more likely to occur. There are several reasons that cloud services are insufficient or unable, but the two most frequent problems are cloud network component or denial of service (DoS) attack at the cloud network servers. Hence, a detection model is designed for DoS attack using the Bi-LSTM classification. In this model, the information regarding the user data is collected and pre-processed using the missing data values replacement and Min-Max normalization technique. These pre-processed data are extracted for features using the Pearson correlation coefficient and classified using the Bi-LSTM algorithm. An alarm message about the DoS assault is sent to the user after its detection, and if the data is not attacked, it is compressed using the LZW compressing algorithm and stored in the cloud. The effectiveness of the proposed model is determined and evaluated with those of the existing techniques. The evaluated performance metrics such as accuracy, error, sensitivity, and precision of the proposed model are 0.98, 0.02, 0.94 and 0.96. Thus, the evaluated values of the designed DoS attack detection model using the Pearson correlation coefficient-based features selection with Bi-LSTM classification and LZW compression technique performs better than the exiting techniques.

I. Introduction

A huge number of gadgets are being connected to the internet as technology develops quickly. Because of the enormous increase in dependence on remote servers, it is essential that these servers be available as needed [1]. Even brief periods of outage can result in significant losses for enterprises. DoS attacks are one of these types of assaults, which carried on an insecure network that may make the services supplied by the businesses unavailable [2]. In a DoS attack, the attacker consumes computing resources by creating an undesirable overload to block legitimate users from finishing their tasks on time. It also controls resource management vulnerabilities caused by logical and programming mistakes in handling network packets [3]. The primary targets of attackers today are government websites, social networking sites, educational institutions, and banking websites. Intrusion Detection Systems (IDSs) are one of the many options available to protect the victim systems from such attacks [4]. IDS can be deployed either on the server-side or the client-side and offers security dependent on the requirements of the user. Conformity of style throughout a conference proceedings. Margins, column widths, line spacing, and type styles are built-in; examples of the type styles are provided throughout this document and are identified in italic type, within parentheses, following the example. Some components, such as multi-levelled equations, graphics, and tables are not prescribed, although the various table text styles are provided. The formatter will need to create these components, incorporating the applicable criteria.