# October 16, 2024

This release introduces **Auto Thresholding** to Detection Models and a new **NetoFlow Connector** container build.

***

**Auto Thresholding for Detection Models**

The new Auto Thresholding feature employs machine learning to automatically adjust threshold values for triggering events in detection models. These thresholds are set based on deviations from normal traffic patterns observed during a learning phase. Once sufficient traffic is collected, the model adjusts the thresholds dynamically. Depending on the configuration, thresholds for Low, Medium, and High severity levels are generated automatically.

For detailed information, see [Auto Thresholding](https://docs.netography.com/docs/detection-auto-thresholding).

**Auto Thresholding Enabled for `anomalous_traffic_s3`**

The `anomalous_traffic_s3` Detection Model, which detects anomalous outbound data over HTTPS to Amazon S3, is the first system Detection Model to include **Auto Thresholding**. This enhancement allows the model to dynamically set thresholds based on observed traffic behavior.

**Additional Documentation for Detection Models**

Additional resources have been provided to help you understand detection models and create your own:

* [Detection Model Quick Reference Guide](https://docs.netography.com/docs/detection-model-quick)
* [Detection Model Configuration](https://docs.netography.com/docs/detection-trackby-thresholds)

If you're creating your own detection model, our Detection Engineers are here to assist you. Connect with us via the `#fusion-detections` channel in Netography's Discord community or contact Support directly.

For more details, visit [Support](https://docs.netography.com/docs/support).

***

**NetoFlow Connector – Now Available as a Container**

The **NetoFlow Connector**, previously available as a Linux software package, is now also available as a Docker-compatible container. This new option simplifies deployment across environments.

For more information on setting up NetoFlow, refer to the following resources:

* [Quickstart: Run NetoFlow](https://docs.netography.com/docs/netoflow-quickstart)
* [Install NetoFlow (Container)](https://docs.netography.com/docs/netoflow-install)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.fusion.vectra.ai/release-notes/2024/october-16-2024.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.