Detect COVID-19 Phishing with Machine Learning

Covid-19 has had a major effect on the world. With millions of people told to self-isolate, the working day for many has been turned on its head. Remote working is now in full swing and companies are running officeless. Whereas this is great for productivity, it increases the danger that cybercriminals pose to companies. With more and more communication being done through email, the opportunity for phishing attacks has never been higher.

Here at Red Sift, we’ve built a machine learning model to distinguish fake COVID-19 messages from the true ones based on the email content. This blog post explains why we took a Machine Learning approach and how we built the model.

Why use Machine Learning?

A traditional rule-based approach to classify email intent isn’t scalable because a large number of rules need to be manually crafted and maintained over time. Attackers are smart and they will constantly find a way to adapt their phishing strategy. For example, to get past a ‘covid-19’ keyword filter, attackers can simply change the keyword to a lookalike one such as ‘côvíd-19’.

Machine Learning uses mathematics and statistics to learn patterns from the data and make educated predictions about unseen data. Machine Learning models need labeled data instead of hand-crafted rules. Machine Learning algorithms can train a model to learn sophisticated and subtle patterns from example phish emails. The model can be easily updated to be more accurate with additional training data collected over time. As a result, an ML-based approach is more robust and dynamic.

Real life examples

This section shows some real-world examples of true and fake COVID-19 messages. Our model correctly classifies them all.

Example 1

Fake WHO message with malicious attachment using accent characters côvíd and misspelling word coronaaviris within the document.

Example 2

Fake government message with malicious links.

A legitimate Covid-19 email

A true COVID message from an organisation.

How we built the model

There are two important building blocks of a machine learning model: data and algorithm.

Data

To effectively train a model, we need to provide a good collection of examples for both fake and true COVID-19 related messages. For true messages, we crowd-source hundreds of messages sent by a large number of different organizations. For fake messages, we filter them from reliable reported phishing messages. To increase variety, we collect fake messages in image format in a number of articles and extract text from them. Luckily, part of working at a cybersecurity company means that there was no shortage of scam messages!

Algorithm

We investigate a number of preprocessing techniques together with different modelling approaches. The preprocessing techniques include both generic text (stop words removal, lemmatization) and email specific (signature exclusion). The modelling techniques range from standard algorithms (logistic regression, naive Bayes, SVM, random forest) to shallow neural networks (word2vec, fasttext) and deep learning (RNN, LSTM). In particular, we make use of the state-of-the-art research in transfer learning including ULMFiT, transformer and BERT.

At Red Sift, we enable security-first organizations to successfully communicate with and ensure the trust of their employees, vendors, and customers. Our portfolio includes a number of gold-standard email and domain protection products: OnDMARC and Brand Trust. These are designed to work in unison to block outbound phishing attacks and provide domain impersonation defense for company-wide threat protection.

Red Sift find out more

PUBLISHED BY

Phong Nguyen

9 Apr. 2020

SHARE ARTICLE:

Categories

Recent Posts

VIEW ALL
BEC

The threat of Business Email Compromise in US healthcare

Jack Lilley

Executive summary: Business Email Compromise is siphoning billions from U.S. healthcare by exploiting human trust instead of software flaws. Spoofed or hijacked messages authorize fraudulent payments, spark ransomware, and expose patient data—causing crippling financial, operational, and compliance damage. Deploying DMARC, MFA, and rigorous multi-person payment checks is now critical. 3 key takeaways Business Email…

Read more
Email

Cloudflare selects Red Sift as a preferred partner to provide DMARC and…

Rebecca Warren

AI-generated email attacks are rapidly growing in scale and sophistication, demanding stronger defenses from at-risk organizations. Starting today, Red Sift is excited to announce a new strategic partnership with Cloudflare, the leading connectivity cloud company, to deliver its market-leading email security application, Red Sift OnDMARC, to a broader global audience.  Today’s alignment enhances Cloudflare’s…

Read more
Cybersecurity

New Zealand moves to mandate DMARC enforcement

Jack Lilley

Executive summary: New Zealand’s Secure Government Email Framework mandates DMARC at p=reject—plus hard-fail SPF, universal DKIM, enforced MTA-STS, and TLS-RPT—by October 2025. The rules replace SEEMail, curb soaring phishing losses, and will affect every organization that emails the public sector. Key takeaways: The New Zealand Government has recently published the Secure Government Email (SGE) Common…

Read more
BEC

DMARC: The best ROI for your organization

Jack Lilley

Executive summary: Implementing DMARC delivers one of the clearest, fastest returns on investment in email security. By authenticating outgoing mail and blocking spoofed messages, DMARC cuts the direct costs of phishing and Business Email Compromise, safeguards brand reputation, and boosts deliverability—ultimately driving revenue and trimming operational workload. Key takeaways: Email is a critical communication tool for…

Read more