DEVELOPING A PREDICTIVE MODEL FOR PHISHING WEBSITE DETECTION USING APACHE SPARK: A SURVEY
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The CB-based URL classifier - as used in this study - stands as evidence of its superior performance, outperforming both the Random Forest and Logistics Regression. The CatBoost algorithm exhibited a high level of competence in discerning the nuances of phishing URLs, thereby elevating the bar for detection accuracy. This model's effectiveness extends beyond the traditional approaches and offers users a real-time shield against phishing websites, fostering a more secure network experience. Also, we were able to address the limitations of sci-kit learn, thereby ushering in improvements in terms of model training efficiency; also, leveraging Apache Spark in combination with Sk-dist paved the way for a more streamlined, responsive, and scalable phishing detection mechanism. This study not only contributes an innovative phishing URL detection model but also underscores the ongoing evolution in the cybersecurity landscape. As the digital realm continues to develop, the symbiosis between advanced machine learning algorithms and powerful frameworks like Apache Spark becomes pivotal in ensuring the resilience of our networks against ever-evolving threats. Through continuous refinement and exploration, the path toward a more secure online ecosystem unfolds, driven by the commitment to stay one step ahead in the ceaseless cat-and-mouse game of cybersecurity.
Fields of Study & Subjects
Spam and Phishing Detection
Misinformation and Its Impacts
Hate Speech and Cyberbullying Detection
Publication details
- Journal / source
- International Journal of Advanced Research in Computer Science
- Volume
- 17
- Issue
- 1
- Pages
- 28–37
- Publication date
- 28 February 2026
- Language
- EN