A Novel Phishing Website Detection Model Based on LightGBM and Domain Name Features

Phishing attacks have evolved in terms of sophistication and increased sheer number recent years. This has led to corresponding developments the methods used evade detection phishing attacks, which pose daunting challenges privacy security users smart systems. study uses LightGBM features domain name propose a machine-learning-based method identify websites maintain Domain features, often known as symmetry, are property wherein multiple domain-name-generation algorithms remain constant. The proposed model is first extract given website, including character-level information on name. filtered improve model’s accuracy subsequently for classification. results experimental comparisons showed that detection, integrates two types training, significantly outperforms single type feature. also higher than other suitable real-time many websites.