An Advanced Algorithm for Email Classification by Using SMTP Code

ABSTRACT

Email is an essential communication tool for modern people and offers a variety of functions. After the outbreak of COVID-19, the importance of emails enhanced further as non-face-to-face work increased. However, with the spread and dissemination of emails, cybercrime that abused emails has also increased. The number of cases of stealing or damaging email users by impersonating public institutions such as the National Police Agency, the Prosecutor’s Office, or the WHO. This study proposes an advanced algorithm of email classification using an SMTP response code to strengthen the level of email security. The proposed system is located on the side of the recipient’s email server and operates upon receipt of the email. When an email is received, it automatically verifies whether the domain of the email sender is normally registered in DNS. Thereafter, MX, SPF, and PTR records are extracted and combined to determine the state of the sending server. When additional verification is required, a proposed algorithm automatically connects the communication session to the sender to request the SMTP response code. The proposed algorithm was applied to two organizations and succeeded in classifying received emails into various categories. This study contributes to the literature on email classification by presenting new ideas in the process of sender verification. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.