Survey on Detection and Prevention of Phishing Websites using Machine Learning

Abstract

This research paper discusses on the phishing websites Prevention and Detection. A phishing website is a common social engineering method that mimics trustful uniform resource locators (URLs) and webpages. Phishing is the most commonly used social engineering and cyber-attack. Through such attacks, the phisher targets naïve online users by tricking them into revealing confidential information, with the purpose of using it fraudulently. In our paper we will be discussing and listing a few of the artificial intelligence models, that will help us to detect these phishing websites so that in the future these data and techniques can be used in machine learning to make our system better and efficient. The problem of phishing is widespread and there is no particular single solution available to effectively reduce all vulnerabilities, so many techniques are often used to reduce certain attacks. Machine learning is a useful tool used to reduce phishing attacks.As innovation keeps on developing, phishing strategies began to advance quickly several anti-phishing tools are available and have their own disadvantages. The paper concentrates on basic Machine learning supervised classification techniques to seek out an answer to phishing attacks. The Basic principle of this paper is to execute the frameworks with good efficiency, exactness, and cost-effectively. The task is attained by using 4 ML managed classification models. The four classification models are KNN, Kernel-SVM, Random Forest Classifier and Decision tree. The supervised classification contains a labeled dataset that is used to train the models. All the four algorithms used: KNN, Kernel-SVM, Random Forest Classifier and Decision tree are classification models. With machine learning, cybersecurity systems can analyze patterns and learn from them to assist prevent similar attacks and answer changing behavior. It can help users to be more active in preventing threats and respond to active attacks in real-time. So, by using Machine Learning, we could progress towards preventing such attacks.