[menog] [Paper] Methodology to Classify Unsolicited Email Threats

[Fahd Batayneh]

Dear All,

 

ICANN’s Office if the Chief Technology Officer (OCTO) published a new paper entitled “Methodology to Classify Unsolicited Email Threats”

https://www.icann.org/en/system/files/files/octo-038-17jan24-en.pdf

 

Email, a fundamental form of communication, faces increasing threats from unsolicited messages. Differentiating these types of threats is essential to take appropriate mitigation measures and deploy effective security controls. It is also an important part of ICANN’s mission to monitor, understand, and report email-based DNS threats. Being able to correctly classify a report as being a genuine threat or not means that ICANN, and others, can have greater confidence in our conclusions.

 

Spam is typically the largest portion of DNS abuse in the data that is listed by reputation feed providers. Therefore, being able to confidently separate spam as a delivery mechanism of malicious content from other types of content is essential for our work.

 

This research delves into the complexities of this issue, examining the diverse categories, inherent threats, and the role of language in classifying unsolicited emails. To build a dataset of 10.8 million unsolicited emails (spam), which cover a period of four and a half years, this study constructed a robust email processing pipeline and methodology for categorizing unsolicited emails into spam, scam, phishing, and adult content.

 

Thank you,

 

Fahd Batayneh

ICANN

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.menog.org/pipermail/menog/attachments/20240209/fc1d128c/attachment.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 4848 bytes
Desc: not available
Url : http://lists.menog.org/pipermail/menog/attachments/20240209/fc1d128c/attachment.bin