Machine Learning Detected a DNS Request With a High DGA Probability Scoreedit
A supervised machine learning model has identified a DNS question name with a high probability of sourcing from a Domain Generation Algorithm (DGA), which could indicate command and control network activity.
Rule type: query
Rule indices:
- logs-endpoint.events.*
- logs-network_traffic.*
Severity: low
Risk score: 21
Runs every: 5m
Searches indices from: now-10m (Date Math format, see also Additional look-back time)
Maximum alerts per execution: 100
References:
Tags:
- Domain: Network
- Domain: Endpoint
- Data Source: Elastic Defend
- Use Case: Domain Generation Algorithm Detection
- Rule Type: ML
- Rule Type: Machine Learning
- Tactic: Command and Control
Version: 3
Rule authors:
- Elastic
Rule license: Elastic License v2
Setupedit
Setup
The rule requires the Domain Generation Algorithm (DGA) Detection integration assets to be installed, as well as DNS events collected by integrations such as Elastic Defend, Network Packet Capture, or Packetbeat.
DGA Detection Setup
The DGA Detection integration consists of an ML-based framework to detect DGA activity in DNS events.
Prerequisite Requirements:
- Fleet is required for DGA Detection.
- To configure Fleet Server refer to the documentation.
- DNS events collected by the Elastic Defend, Network Packet Capture integration, or Packetbeat.
- To install Elastic Defend, refer to the documentation.
- To add the Network Packet Capture integration to an Elastic Agent policy, refer to this guide.
- To set up and run Packetbeat, follow this guide.
The following steps should be executed to install assets associated with the DGA Detection integration:
- Go to the Kibana homepage. Under Management, click Integrations.
- In the query bar, search for Domain Generation Algorithm Detection and select the integration to see more details about it.
- Under Settings, click Install Domain Generation Algorithm Detection assets and follow the prompts to install the assets.
Ingest Pipeline Setup
Before you can enable this rule, you’ll need to enrich DNS events with predictions from the Supervised DGA Detection model. This is done via the ingest pipeline named <package_version>-ml_dga_ingest_pipeline installed with the DGA Detection package.
- If using an Elastic Beat such as Packetbeat, add the DGA ingest pipeline to it by adding a simple configuration setting to packetbeat.yml.
- If adding the DGA ingest pipeline to an existing pipeline, use a pipeline processor.
Adding Custom Mappings
- Go to the Kibana homepage. Under Management, click Stack Management.
- Under Data click Index Management and navigate to the Component Templates tab.
- Templates that can be edited to add custom components will be marked with a @custom suffix. Edit the @custom component template corresponding to the beat/integration you added the DGA ingest pipeline to, by pasting the following JSON blob in the "Load JSON" flyout:
{
"properties": {
"ml_is_dga": {
"properties": {
"malicious_prediction": {
"type": "long"
},
"malicious_probability": {
"type": "float"
}
}
}
}
}
Rule queryedit
ml_is_dga.malicious_probability > 0.98
Framework: MITRE ATT&CKTM
-
Tactic:
- Name: Command and Control
- ID: TA0011
- Reference URL: https://attack.mitre.org/tactics/TA0011/
-
Technique:
- Name: Dynamic Resolution
- ID: T1568
- Reference URL: https://attack.mitre.org/techniques/T1568/
-
Sub-technique:
- Name: Domain Generation Algorithms
- ID: T1568.002
- Reference URL: https://attack.mitre.org/techniques/T1568/002/