Detection of coronavirus phishing emails using echo state neural network

Abstract EN

E-mail is an important and fast mean of conveying information among people, banks, companies and organizations, that information is often important, sensitive and secret, this make it worthy to attackers who can use it for harmful purposes.

Spread of coronavirus in most countries of the world and the huge amount of media coverage surrounding this virus led to emergence phishing emails by exploiting coronavirus pandemic.

Phishing emails are scam messages used by fraudsters to take out secret information from persons by pretending that it is from official sources.

In this paper a novel method has been proposed to detect the coronavirus phishing emails and distinguish them from legitimate mails by using Echo state neural network(ESN), after preprocessing the emails, features are selected from the header and body of it, these features are given as fed to the (ESN) algorithm to classify emails as malicious or legitimate.

The results showed the efficiency and accuracy of the algorithm used in the detection of coronavirus phishing emails, where the rate of accuracy, precision, recall and F-measure are 99.392, 98.892, 99888, and 99.387 respectively with low required processing time (0.00092 msec.) for testing and (165.19 msec.) for training.