> For the complete documentation index, see [llms.txt](https://davidjosearaujo.gitbook.io/online-courses/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://davidjosearaujo.gitbook.io/online-courses/cyber-threat-hunting/threat-hunting-techniques-and-generative-ai/anomalies-and-baselining.md).

# Anomalies and baselining

## Anomaly detection

**Anomaly detection** is a threat hunting technique that involves analyzing data to identify abnormal patterns or behaviors that may indicate a security threat

* This technique relies on statistical models and machine learning algorithms to detect deviations from normal patterns of behavior
* Anomaly detection can be applied to various data sources, including network traffic logs, system logs and user behavior data
* By analyzing data for anomalies, security teams can identify potential threats that may have gone unnoticed by traditional security tools
* For example, anomaly detection can be used to identify unusual network traffic patterns that may indicate a distributed denial-of-service (DDoS) attack or to detect abnormal user behavior that may indicate a compromised account

One of the benefits of anomaly detection is that it can be used to detect both **known** and **unknown threats**

Because anomaly detection relies on statistical models and machine learning algorithms, **it can detect patterns that may be too subtle or complex** for humans or traditional security tools to identify

Overall, anomaly detection is a valuable threat hunting technique that can help organizations detect and respond to security threats mode effectively

By identifying anomalous behavior, security teams can take proactive steps to mitigate potential threats before they cause significant damage