Most of the cyber breaches in the world today are done based on fraudulent activities. Phishers and Spammers come up with new and hybrid techniques all the time to circumvent the available software and techniques, which shows that all organizations are covered by unbroken threat. Among the approaches developed to stop email spam and phishing, filtering is a popular and important one. Common uses of email filters include organizing incoming emails and removal of spam, while phishing is detected by validating email body, URLs, etc. In this study, we proposed an ensemble approach for phishing and spam filter-based feature selection methods with the goal to lower the feature space dimensionality and increase the accuracy of spam and phishing review classification. We collected different public datasets and trained on Machine Learning (ML) based mRMR (Minimum Redundancy Maximum Relevance) models and Ensemble models. Experimental results with seven classifiers show an average of 83% accuracy which made the feature selector improves the performance of spam and phishing classifiers. And can legitimate future email cyber-attacks with a scope for future research and expansion.

Detection of Phishing and Spam Emails Using Ensemble Technique

Emails are inevitable in this modern era. It has become an effective tool in the communication field. Because of its easiness the number of users are increasing day-by-day. With the increased number of email users, the number of spam mails have also increased. Spam can cause great loss to users. Many spam filtering techniques have been introduced to distinguish between ham and spam. A mail that appear as spam may appear as ham to another user and vice versa. That is, it depends on the personal preference of user. Therefore an ontology based personalized mail access is necessary. This paper compares the ontology based spam filtering and conventional spam filtering.

V Bindu

Papers

Conventional and Ontology Based Spam Filtering