An intelligent intrusion detection system to prevent URL redirection attack

Abstract

In today’s digital age, the widespread use of social networking platforms like Facebook, Twitter, and Instagram, alongside messaging services such as Email and WhatsApp, has increased the convenience of communication. However, this accessibility has also provided a fertile ground for cybercriminals and spammers to exploit these platforms through URL redirection attacks, which are often used to steal sensitive user information. Existing solutions, including machine learning (ML), deep learning (DL), and ensemble methods have been employed to combat such threats. Despite their effectiveness, these approaches struggle to detect emerging types of attacks and suffer from limitations when dealing with imbalanced data, leading to reduced detection performance. To address these challenges, this research introduces an improved extreme gradient boosting (IXGB) algorithm that optimizes the weight adjustments in the model, aiming to enhance the detection of malicious URLs. The proposed method focuses on improving classification accuracy, especially for new or unseen types of attacks. Experimental results on a standard dataset demonstrate that IXGB achieves superior accuracy compared to traditional models, making it a promising approach for enhancing cybersecurity on social media and messaging platforms.