Cryptography and Optimization-Driven Support Vector Neural Network to Mitigate DoS Attacks in E-Commerce

Abstract

Nowadays, cloud computing has become a significant area for the business due to the high demand of people engaging in E-commerce. E-commerce applications are very popular for conducting business via the Internet which includes online banking, bill payment, and purchasing goods, etc. E-commerce is said to be more straightforward, easier to use, intuitive, and less threatening. The rapid development of the Internet over the past decade appeared to have facilitated an increase in the incidents of online attacks. One such powerful and harmful attack is the denial-of-service (DoS) attack, and hence, protecting the entities from such attacks is essential. Therefore, an effective DoS attack detection technique is required in the E-commerce transactions to offer security in this platform. Accordingly, in this paper, a technique is developed for DoS attack detection in the E-commerce transactions by proposing glowworm swarm optimization-based support vector neural network (GSO-SVNN)-based authorization. The security will be provided with elliptic-curve cryptography (ECC) and hashing function to show the strength of the security protocol against a DoS attacks. The performance of the proposed technique is evaluated using four metrics, like accuracy, precision, recall, and false positive rate (FPR).