Over a billion subscribers are served by cloud hosting services, which give them stable, affordable, dependable, high-speed, and internationally accessible resource access. Users frequently watch out for warning indicators of phishing attacks, such as websites with suspicious-looking domain names or those that lack an HTTPS certificate. Phishers often utilize social engineering tactics or create false websites to deceive their victims into divulging sensitive information such as account IDs, usernames, and passwords. This information can be used to steal money from individuals and corporations. Phishers have devised techniques to get around the many strategies to detect phishing websites. Nonetheless, these strategies have been put in place. Machine learning is one of the most effective methods for identifying potentially harmful behaviors. This is done so that approaches based on machine learning can identify the common features shared by the vast majority of phishing attacks. This research intends to train machine learning models and deep neural networks using the dataset produced to identify phishing websites. It is necessary to gather both phishing and benign URLs of websites to generate a dataset from which it will be possible to derive the required URLand website content-based features. In this work, we compared the accuracy of the predictions made by several different machine-learning approaches for detecting phishing websites

Cybercrime, Machine learning, Cloud, Phishing attacks, Classification