Overview

Using unsupervised machine learning technology, Prelert analyzes massive amounts of data in near-real time to pinpoint anomalous behavior of humans or machines. This helps security teams find known and unknown threats as they’re occurring, without the need to manually set any rules or thresholds. It reduces false positives while scoring and prioritizing the most important alerts to help security teams cut through the noise and focus on the critical issues. It can link anomalies together based on common entities (such as users, IP addresses or domains) to give IT teams a complete picture and let the data tell the story behind advanced cyber threats. As a result, organizations can act more quickly and effectively to remediate issues before they impact business.

In addition, Prelert brings analytics to where the data resides through integrations with Elasticsearch and Splunk, and an open API that allows enterprise users and developers, cloud service providers and technology vendors to use Prelert in their own products or environments.

Prelert is the only behavioral analytics platform that can be quickly and easily applied to a broad set of use cases, such as user-based security, network security, server security, database security and many others. While other solutions – including those built with supervised machine learning – require highly trained professionals to figure out how to write and modify existing models, Prelert’s use of unsupervised machine learning is more easily and quickly deployed. It’s also smarter. For example, it’s capable of distinguishing normal behavior based on periodicity – such as the time of day or day of the week – and readjusting on its own as behaviors change over time. This means less maintenance by highly trained (and paid) professionals, and less false positives to investigate.