Detection: Detect suspicious DNS TXT records using pretrained model in DSDL

Description

The following analytic identifies suspicious DNS TXT records using a pre-trained deep learning model. It leverages DNS response data from the Network Resolution data model, categorizing TXT records into known types via regular expressions. Records that do not match known patterns are flagged as suspicious. This activity is significant as DNS TXT records can be used for data exfiltration or command-and-control communication. If confirmed malicious, attackers could use these records to covertly transfer data or receive instructions, posing a severe threat to network security.

Search

 1
 2| tstats `security_content_summariesonly` count min(_time) as firstTime max(_time) as lastTime FROM datamodel=Network_Resolution
 3  WHERE DNS.message_type=response
 4    AND
 5    DNS.record_type=TXT
 6  BY DNS.src DNS.dest DNS.answer
 7     DNS.record_type
 8
 9| `drop_dm_object_name("DNS")`
10
11| rename answer as text
12
13| fields firstTime, lastTime, message_type,record_type,src,dest, text
14
15| apply detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl
16
17| rename predicted_is_unknown as is_suspicious_score
18
19| where is_suspicious_score > 0.5
20
21| `security_content_ctime(firstTime)`
22
23| `security_content_ctime(lastTime)`
24
25| table src,dest,text,record_type, firstTime, lastTime,is_suspicious_score
26
27| `detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl_filter`

Data Source

No data sources specified for this detection.

Macros Used

Annotations

Default Configuration

This detection is configured by default in Splunk Enterprise Security to run with the following settings:

Implementation

Steps to deploy detect suspicious DNS TXT records model into Splunk App DSDL. This detection depends on the Splunk app for Data Science and Deep Learning which can be found here - https://splunkbase.splunk.com/app/4607/ and the Network Resolution datamodel which can be found here - https://splunkbase.splunk.com/app/1621/. The detection uses a pre-trained deep learning model that needs to be deployed in DSDL app. Follow the steps for deployment here - https://github.com/splunk/security_content/wiki/How-to-deploy-pre-trained-Deep-Learning-models-for-ESCU.

• Download the artifacts .tar.gz file from the link - https://seal.splunkresearch.com/detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.tar.gz.
• Download the detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.ipynb Jupyter notebook from https://github.com/splunk/security_content/notebooks.
• Login to the Jupyter Lab assigned for detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl container. This container should be listed on Containers page for DSDL app.
• Below steps need to be followed inside Jupyter lab.
• Upload the detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.tar.gz file into app/model/data path using the upload option in the jupyter notebook.
• Untar the artifact detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.tar.gz using tar -xf app/model/data/detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.tar.gz -C app/model/data.
• Upload detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.ipynb` into Jupyter lab notebooks folder using the upload option in Jupyter lab.
• Save the notebook using the save option in Jupyter notebook.
• Upload detect_suspicious_dns_txt_records_using_pretrained_model_in_dsdl.json into notebooks/data folder.

Known False Positives

False positives may be present if DNS TXT record contents are similar to benign DNS TXT record contents.

Associated Analytic Story

• DNS Hijacking

• Suspicious DNS Traffic

• Command And Control

• VoidLink Cloud-Native Linux Malware

References

• https://attack.mitre.org/techniques/T1071/004/

• https://unit42.paloaltonetworks.com/dns-tunneling-how-dns-can-be-abused-by-malicious-actors/

• https://en.wikipedia.org/wiki/TXT_record

Detection Testing

Replay any dataset to Splunk Enterprise by using our replay.py tool or the UI. Alternatively you can replay a dataset into a Splunk Attack Range

Source: GitHub |

Version: 8