• Arun Kumar M S
• Sumithra P N
• Vidya Y S
• Vaishnavi P N

Phishing, a widespread cybercrime, employs camouflaged websites to trick users into disclosing sensitive information or downloading malware. With the advancement of artificial intelligence, researchers increasingly rely on machine learning (ML) and deep learning (DL) algorithms for identifying phishing websites. This study conducts experiments to compare different ML and DL methods, with ensemble ML algorithms demonstrating superior accuracy and computational efficiency, even with reduced feature datasets. The paper also discusses why ensemble ML methods are well-suited for binary phishing classification in dynamic environments. Additionally, a proposed multilayered stacked ensemble learning technique achieves notable performance improvements across various datasets, with accuracies ranging from 96.79% to 98.90%. This method simplifies feature extraction and reduces processing overhead, resulting in high accuracy rates for detecting phishing websites. Despite ongoing advancements in anti-phishing techniques, challenges persist due to the evolving nature of phishing attacks, highlighting the ongoing need for research to effectively combat this cyber threat.

Phishing websites detection ,cybersecurity, machine learning, ensemble learning, deep learning.

"PHISHING WEBSITES DETECTION USING MACHINE LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.d87-d91, May-2024, Available :http://www.jetir.org/papers/JETIR2405307.pdf

"PHISHING WEBSITES DETECTION USING MACHINE LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppd87-d91, May-2024, Available at : http://www.jetir.org/papers/JETIR2405307.pdf