An Analysis of Malicious URL Detection Using Deep Learning

Abstract

Considerable progress has been achieved in the digital domain, particularly in the online realm where a multitude of activities are being conducted. Cyberattacks, particularly malicious URLs, have emerged as a serious security risk, deceiving users into compromising their systems and resulting in annual losses of billions of dollars. Website security is essential. It is critical to quickly identify dangerous or bad URLs. Blacklists and shallow learning are two techniques that are being investigated in response to the threat posed by malicious URLs and phishing efforts. Historically, blacklists have been used to accomplish this. Techniques based on blacklists have limitations because they can't detect malicious URLs that have newly generated. In order to overcome these challenges, recent research has focused on applying machine learning and deep learning techniques. By automatically discovering complex patterns and representations from unstructured data, deep learning has become a potent tool for recognizing and reducing these risks. The goal of this paper is to present a thorough analysis and structural comprehension of Deep Learning based malware detection systems. The literature review that covers different facets of this subject, like feature representation and algorithm design, is found and examined. Moreover, a precise explanation of the role of deep learning in detecting dangerous URLs is provided.