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.


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!


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.

All this work means that we are able to give you 360° Email Protection at this tricky time, with OnDMARC preventing email impersonation, OnINBOX protecting you from inbound email threats, and OnDOMAIN securing your domain perimeter.

Red Sift find out more


Phong Nguyen

9 Apr. 2020



Recent Posts


The best tools to protect yourself from SubdoMailing

Francesca Rünger-Field

In late February 2024, ‘SubdoMailing’ became a trending search term overnight. Research by Guardio Labs uncovered a massive-scale phishing campaign that had been going on since at least 2022. At the time of reporting, the campaign had sent 5 million emails a day from more than 8,000 compromised domains and 13,000 subdomains with several…

Read more
Product Release

Red Sift’s Spring 2024 Quarterly Product Release

Francesca Rünger-Field

This early into 2024, the cybersecurity space is already buzzing with activity. Emerging standards, such as Google and Yahoo’s bulk sender requirements, mark a new era of compliance for businesses reliant on email communication. At the same time, the prevalence of sophisticated cyber threats, such as the SubdoMailing campaign, emphasizes the continual hurdles posed…

Read more

Navigating the “SubdoMailing” attack: How Red Sift proactively identified and remediated a…

Rebecca Warren

In the world of cybersecurity, a new threat has emerged. Known as “SubdoMailing,” this new attack cunningly bypasses some of the safeguards that DMARC sets up to protect email integrity.  In this blog we will focus on how the strategic investments we have made at Red Sift allowed us to discover and protect against…

Read more

Where are we now? One month of Google and Yahoo’s new requirements…

Rebecca Warren

As of March 1, 2024, we are one month into Google and Yahoo’s new requirements for bulk senders. Before these requirements went live, we used Red Sift’s BIMI Radar to understand global readiness, and the picture wasn’t pretty.  At the end of January 2024, one-third of global enterprises were bound to fail the new…

Read more