Abnormal Security Engineering Blog
Tales from Abnormal Engineering as we build the next generation of AI cybersecurity
Re-Scoring an ML Detection Engine on Past Attacks (part 1)
Re-Scoring an ML Detection Engine on Past Attacks (part 1)
Developing a machine learning product for cybersecurity comes with unique challenges. For a bit of background, Abnormal Security’s…
Outgrowing your In-Memory DB and Scaling with Microservices
Outgrowing your In-Memory DB and Scaling with Microservices
How we tackled memory bottlenecks and achieved 10x scalability
A Story of Debugging an Unexpectedly Slow SQL Query Powering our Dashboards
A Story of Debugging an Unexpectedly Slow SQL Query Powering our Dashboards
How a simple query can be super slow
Graph of Models and Features
Graph of Models and Features
At the core of all Abnormal’s detection products sits a sophisticated web of prediction models. For any of these models to function we…
Lazily Loading ML Models for Scoring with PySpark
Lazily Loading ML Models for Scoring with PySpark
Authors: Jeshua Bratman and Vineet Edupuganti
Stopping New Email Attacks with Data Augmentation and Rapidly-Training Models
Stopping New Email Attacks with Data Augmentation and Rapidly-Training Models
On October 21st 2020, just two weeks before the US general election, many voters in Florida received threatening emails purportedly from…
