Abstract: The scope and severity of network concerns about information security have increased over time. Nowadays, most hacking methods target technology from start to finish while also exploiting human frailties. Pharming, phishing, and social engineering are just a few of these methods. One of the aspects of these Using damaging URRs to fool consumers is considered an assault (URLs). This is why identifying malicious Content is a hot issue right now. A variety of academic research has demonstrated several ways to identify malicious URLs using machine learning and deep learning technologies. Based on our hypothesized URL behaviours and characteristics, we provide a machine learning-based solution for detecting malicious URLs in this work. Furthermore, big data technology is applied to enhance the ability to appreciate fraudulent URLs based on aberrant activity. The proposed detection approach consists of a novel set of URL attributes and behaviours, a machine learning algorithm, and big data technologies. The results of the experiment indicate that the stated URL characteristics and behaviour can improve overall ability to identify risky URLs. This implies that consumers may successfully detect risky URLs using the suggested methods.
Keywords: phishing, machine learning, malicious URL detection.
|
DOI:
10.17148/IJARCCE.2023.12223
