Paper Title
Safe Click- Detection of Phishing Websites Using Machine Learning

Abstract
Phishing is one of those types that have been around for centuries, but still represent a gigantic cyber attack problem that affects individuals and institutions around the world. It is also important to know in order to protect users' identity, money and private data from malicious activities carried out in the cyber world. A new approach is proposed to detect and avoid phishing sites through list-based detection, similarity-based methods, and implementation of artificial intelligence algorithms. Discusses list-based techniques based on blacklists of known phishing URLs and the challenges of maintaining these lists due to changes in phishing methods. It also considers similarity-based approaches that take into account the similarity of URLs and website features, including both textual and visual parts, to identify threats. In addition, it explores machine learning models that rely on multiple features to classify web pages in an attempt to bridge the URL shortening gap and the lack of adaptability and dynamic feature extraction. There is currently a significant gap in research that now a days attackers rely heavily on URL shortening services to mask real phishing URLs. The project evaluates the latest data sets used to test these approaches. This will help improve detection of phishing threats and overall cyber security resilience. Keywords - Phishing Detection, List-Based Methods, Similarity-Based Techniques, Machine Learning.