Abnormal Blog

If an advanced attack finds its way into an employee’s inbox, you hope that they remember their security and awareness training and do not engage with it. However, there is always the risk that they engage with the message—clicking a...

Machine learning engineering is hard, especially when developing products at high velocity, as is the case for us at Abnormal Security. Typical software engineering lifecycles often fail when developing ML systems.

Developing a machine learning product for cybersecurity comes with unique challenges. For a bit of background, Abnormal Security’s products prevent email attacks—think credential phishing, business email compromise, and malware—and also...

You’ll find similar characteristics in BEC that you will in VEC. A common trait of BEC is it does not contain malware or malicious URLs, and due to that technique, it is able to bypass conventional email security measures like SEGs. BEC relies...

IRS email impersonations are widespread across all industries. These attacks vary in scale and victim, targeting both individuals and companies as a whole. This particular attack follows the growing trend of utilizing social engineering strategies for malicious engagement...

To detect account takeovers, Abnormal Security’s machine learning algorithms utilize many factors related to location, devices, and applications. However, until now, much of that information was not exposed to users. In an effort to be as customer-centric as possible...

In a recent post, our Head of Platform & Infrastructure Michael Kralka discussed how Abnormal’s rapid growth has forced us to make our core services horizontally scalable. In-memory datasets that start off small become huge memory...

Abnormal Security has a data-driven culture that permeates the entire organization, from the engineering team to product, sales, and beyond. We make decisions by analyzing data monitoring relevant metrics. For online analytics, we use a great tool called Grafana...

At Abnormal Security, we’re constantly exploring opportunities to improve our customer’s user experience. In this blog post, we’d like to share Abnormal’s process to design a framework to identify gaps and improve customer’s first-time user experience to onboard our platform.

Abnormal Security prides itself on its differentiated technology and superior efficacy when it comes to stopping advanced email attacks. Despite the overwhelming effectiveness of our platform, like all advanced AI systems...

In this attack, attackers impersonate a company's Human Resources department and send a COVID-19 scan via a lookalike Microsoft Office 365 email. The original message to the recipient appears to originate from the company’s internal human resources email address.

This January, I joined Abnormal Security as a new grad Software Engineer. As you might expect in the midst of the COVID-19 pandemic, the onboarding process was entirely remote. Prior to graduating from MIT with my BS in Electrical Engineering and Computer Science, I had interned...

When attempting to gain credentials to a Google account, the best brand to impersonate is likely Google. In this account, threat actors sent an urgent account message to trick recipients into inputting their Google credentials, hoping to trick...

The prolific attack on SolarWinds and their partner ecosystem will forever change how we view supply chain security and the role email communication plays in it. As the events and details surrounding the attack continue to unfold, we have learned from the company itself...

The primary value that Abnormal brings to email security is an advanced, ML-based detection system that can extract and analyze thousands of signals, identify patterns, and adapt over time to detect important attacks–without relying exclusively on threat intel or...

At the core of all Abnormal’s detection products sits a sophisticated web of prediction models. For any of these models to function, we need deep and thoughtfully engineered features, careful modeling of sub-problems, and the ability to join data from a set of databases. For example, one type of email attack...

In a recent attack uncovered by Abnormal Security, the attacker impersonates LinkedIn to send a malicious attachment that could lead to identity theft. Once the attachment is opened, the victim is asked to put in personal identifying information, including their social security number.

Abnormal Security recently detected two new types of attacks where scammers are targeting victims by redirecting their own Microsoft 365 out-of-office replies as well as read receipts back to them. These tactics indicate attackers are using every available tool and loophole...

At Abnormal, the problems we are trying to solve are not that much different from those being tackled by other organizations, including large enterprises. What is unique to startups are the additional constraints placed on the solution space, such as the amount...

PayPal is a well-known money transfer application, used often between friends and family as well as for small businesses. Because PayPal accounts are often linked to credit cards and bank accounts, the company itself is a commonly impersonated brand from attackers...

Because they contain the keys to the financial kingdom and allow attackers direct access to money, banks tend to be some of the most impersonated organizations. In this attack, attackers mimic an automated notification from BB&T in order to steal recipients' online banking...

Attackers impersonated USPS while sending out phishing emails designed to steal payment credentials.

Cybercriminals attempted a phishing scam to access cryptocurrency wallets by impersonating Ledger.

Scammers impersonated the Department of Labor and offered supposed relief funds to phish sensitive and identifying information.