A SYSTEM FOR THE DETECTION OF MALICIOUS DOMAIN NAMES USING IMPROVED DEEP-LEARNING MODEL

The tremendous growth of innovative technologies used for online services in the global economic space brings vulnerabilities to security breaches. The upsurge of these vulnerabilities created a level playing field for cyber-attacks to flourish, with assailants constantly adapting new nefarious methods to compromise information and deceive naïve users of the cyberspace. Despite the amazing and numerous anti-phishing approaches and solutions, the increasing incidences caused by malicious domain name system attacks such as spam, phishing and malware could be attributed to the dynamism in the approaches used by cyber criminals to counterfeit the techniques. To address these issues, many cyber security researchers have switched their focus to machine learning-based methodologies for malicious DNS detection. In this paper, we introduced the usage of machine-based model to detect the dynamism of malicious DNS by exploring Machine Learning, Ensemble learning and Deep-Learning. A customized web Crawler was implemented to extract URL attribute for model extraction. Furthermore, a Cross validation approach was used towards the classification and regression metrics (statistical approach) to evaluate their performance to an accuracy of 89.9%. Our experiment is based on both active and passive DNS analysis.