Key points are not available for this paper at this time.
This paper introduces the escalating risk of network information insecurity, driven by hackers’ tactics such as exploiting end-to-end technology and human vulnerabilities like social engineering, phishing, and pharming. A common strategy in these attacks involves deceiving users with malicious Uniform Resource Locators (URLs), prompting a critical need for effective malicious URL detection methods. Recent scientific studies have explored various machine learning and deep learning approaches for this purpose. Our paper presents a novel method for detecting malicious URLs, leveraging machine learning techniques based on unique URL behaviours and attributes. Additionally, big data technology is employed to enhance detection capabilities by identifying abnormal behaviours. Our proposed detection system integrates a new set of URL features and behaviours, a machine learning algorithm, and big data technology. Experimental results indicate significant improvements in malicious URL detection efficacy using our approach, suggesting it as an optimized and user-friendly solution for addressing the malicious URL threat.
Building similarity graph...
Analyzing shared references across papers
Loading...
Rao et al. (Fri,) studied this question.
www.synapsesocial.com/papers/68e72f5cb6db6435876a90e7 — DOI: https://doi.org/10.58599/ijsmien.2024.2301
Runlong Rao
Khadeer Shaik
Khaja Babu Shaik
International Journal of Scientific Methods in Intelligence Engineering Networks
Building similarity graph...
Analyzing shared references across papers
Loading...