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.