Abstract: As a means of contact for personal and professional use, emails are commonly used. Information shared that emails, such as banking information, credit reports, login details, etc., is often sensitive and confidential. This makes them useful for cyber criminals who are able to exploit the data for malicious purposes. Phishing is a technique that fraudsters use to acquire confidential data from individuals by claiming to be from proven sources. The sender will persuade you to provide personal information under bogus pretences in a phished email. Phishing website detection is an intelligent and efficient model focused on the use of data mining algorithms for classification or association. In order to identify the phishing website and the relationship that correlates them with each other, these algorithms were used to identify and characterize all rules and factors so that we detect them by their efficiency, accuracy, number of generated rules and speed. The proposed system integrates both classification and association algorithms, which optimize the system more effectively and faster than the current system. The error rate of the current system decreases by 30 percent by using these two algorithms with several protocols, so that the proposed system creates an effective way to detect the phishing website by using this approach. While there is no device that will detect the entire phishing website, it can create a more effective way to detect the phishing website using these methods. Spam emails can be only annoying but also dangerous to consumer. People using them for illegal and unethical conducts, phishing and fraud.
Keywords: Machine learning, Natural Language Processing (NLP), Feature extraction, Feature selection.
|
DOI:
10.17148/IJARCCE.2021.10424
