Abnormal Blog

Learn how Abnormal Security leverages large language models (LLMs) to enhance security awareness and automate SOC teams’ workflows with AI Security Mailbox.

Discover how Abnormal Security leverages AI and decision trees to extract signals, analyze context, and detect sophisticated email threats with high accuracy.

Learn how Abnormal Security leverages large language models (LLMs) thoughtfully with safeguards and GenAI-based quality assurance testing.

Discover how Abnormal Security leverages large language models (LLMs) to automate and enhance email threat detection with AI-generated detection rules.

Learn how Abnormal uses natural language processing or NLP to protect organizations from phishing, account takeovers, and more.

We recently shared a look at how the Abnormal engineering team overhauled our Unwanted Mail service architecture to accommodate our rapid growth. Today, we’re diving into how the team migrated traffic to the new architecture—with zero downtime.

In episode 11 of Abnormal Engineering Stories, David Hagar, Director of Engineering and Abnormal Head of UK Engineering, continues his conversation with Zehan Wang, co-founder of Magic Pony.

As our customer base has expanded, so has the volume of emails our system processes. Here’s how we overcame scaling challenges with one service in particular.

In episode 10 of Abnormal Engineering Stories, David Hagar, Director of Engineering and Abnormal Head of UK Engineering, sits down with Zehan Wang, co-founder of Magic Pony.

Learn how explicitly modeling dependencies in a machine learning pipeline can vastly reduce its complexity and make it behave like a tower of Legos: easy to change, and hard to break.

In episode 9 of Abnormal Engineering Stories, Dan sits down with Mukund Narasimhan to discuss his perspective on productionizing machine learning.

As we’ve scaled our customer base, the size of our datasets has also grown. With our rapid expansion, we were on track to hit the data storage limit of our Redis server in two months, so we needed to figure out a way to scale beyond this—and fast!

At Abnormal, we pride ourselves on our excellent machine learning engineering team. Here are some patterns we use to distinguish between effective and ineffective ML engineers.

In episode 8 of Abnormal Engineering Stories, Kevin interviews Saminda Wijegunawardena, an engineering leader who is no stranger to fast-growing enterprise startups.

There are many approaches to ensuring our system can adapt quickly to new attack trends. One of the most successful approaches we’ve found is to take in the newest attacks and retrain our system end-to-end to detect them.

Here at Abnormal, our machine learning models help us spot trends and abnormalities in customer data in order to catch and prevent cyberattacks.

Abnormal's fundamental job is to detect malicious emails like phishing and business email compromise attacks and other malicious events, such as suspicious sign-ins that indicate an account has been hacked.

Tim Tully, Partner at Menlo Ventures, grew up in Silicon Valley, where a love for coding was kindled in him. Tim is a technologist to the core, which innately led him to become an elite technical leader at companies like Splunk and Yahoo.

At a hyper-growth startup, a solution from six months ago will unfortunately no longer scale. The business is growing rapidly, and this traffic to this service in particular was growing at an unprecedented rate. We hit a point where it needed re-architecting to support 10x the current scale.

At Abnormal Security, we use a data science-based approach to keep our customers safe from the most advanced email attacks. This requires processing huge amounts of data to train machine learning models, build datasets, and otherwise model the typical behavior of the organizations we’re protecting.

Tony Dong, Director of Engineering at Rippling, is no stranger to the diverse set of engineering problems that fast-growing startups create. Before building and leading his teams at Rippling, Tony was CTO and co-founder at PerShop, a YC backed startup, and Senior Engineer at Twitter, Periscope, and TellApart.

As Abnormal grows, we have to maintain a scalable codebase across all areas of engineering to prevent issues around testing, maintainability, and documentation. When organizations scale, a common problem is that the codebase becomes cluttered, with multiple teams writing different code that accomplishes the same task.

Many companies aspire to be customer-centric, but few find a way to operationalize customer-centricity into their team’s culture. As a 3x SaaS startup founder, most recently at Orum, and a veteran of Facebook and Palantir, Ayush Sood...

Working at hyper-growth startups usually means that unreasonable expectations will be thrust on individuals and teams. Demanding timelines, goals, and expectations can lead to high pressure, stress, accountability, and ultimately, extraordinary growth and achievements.