Enhancing Trust and Privacy in E-Commerce Platforms by Preventing DNS Heavyweight Attacks
Ankita Kumari, Ishu Sharma · 2023
E-commerce is the largest platform of online business that provides users with a virtual environment for interaction related to buying and selling tasks. People prefer to purchase online to have more variety of products and to get items at discounted prices. But data privacy is a big concern in such scenarios where the user is communicating with E-Commerce platforms using their personal and financial details. The attacker can easily target the user and breach the data/ information and login credentials of the user by cyberattacks like domain name system attacks. Ingenious solutions for the early identification of Domain Name assaults for various e-commerce platforms may now be available as machine learning solutions can be deployed in real network environments as well. The strategy proposed in this research paper serves as a protective barrier for the Ecommerce platforms to prevent the breaching the information. The methodology is suggested to employ a trained machine smart loader chip for attack detection to make sure that only allowed data packets are transmitted to the domain name system server of the e-commerce system. The dataset used to train and test artificial intelligence algorithms is derived from the data repository of the Canadian Institute for Cyber Security. According to the findings, the decision tree classifier is the most effective technique for spotting domain name system attack infections at an early stage.