LLM Model File Creation
Description
Detects the creation of Large Language Model (LLM) files on Windows endpoints by monitoring file creation events for specific model file formats and extensions commonly used by local AI frameworks. This detection identifies potential shadow AI deployments, unauthorized model downloads, and rogue LLM infrastructure by detecting file creation patterns associated with quantized models (.gguf, .ggml), safetensors model format files, and Ollama Modelfiles. These file types are characteristic of local inference frameworks such as Ollama, llama.cpp, GPT4All, LM Studio, and similar tools that enable running LLMs locally without cloud dependencies. Organizations can use this detection to identify potential data exfiltration risks, policy violations related to unapproved AI usage, and security blind spots created by decentralized AI deployments that bypass enterprise governance and monitoring.
Query · spl
| tstats `security_content_summariesonly` count
min(_time) as firstTime
max(_time) as lastTime
from datamodel=Endpoint.Filesystem where
(
Filesystem.file_name IN (
"*.gguf",
"*.safetensors",
"*ggml.dll",
"*modelfile*"
)
OR
(
Filesystem.file_name = "ggml-*"
Filesystem.file_name = "*.dll"
)
)
NOT Filesystem.file_name IN (
"__PSScriptPolicyTest*",
"*.csv",
"*.doc",
"*.docx",
"*.jpeg",
"*.jpg",
"*.pdf",
"*.png",
"*.ppt",
"*.pptx",
"*.py",
"*.xls",
"*.xlsx",
"*Bentley.Civil*"
)
by Filesystem.action Filesystem.dest Filesystem.file_access_time Filesystem.file_create_time
Filesystem.file_hash Filesystem.file_modify_time Filesystem.file_name Filesystem.file_path
Filesystem.file_acl Filesystem.file_size Filesystem.process_guid Filesystem.process_id
Filesystem.user Filesystem.vendor_product
| `drop_dm_object_name(Filesystem)`
| `security_content_ctime(firstTime)`
| `security_content_ctime(lastTime)`
| `llm_model_file_creation_filter`
Implementation guide
To successfully implement this search, you need to be ingesting logs with file creation events from your endpoints.
Ensure that the Endpoint data model is properly populated with filesystem events from EDR agents or Sysmon Event ID 11.
The logs must be processed using the appropriate Splunk Technology Add-ons that are specific to the EDR product.
The logs must also be mapped to the Filesystem node of the Endpoint data model.
Use the Splunk Common Information Model (CIM) to normalize the field names and speed up the data modeling process.
Known false positives
- Legitimate creation of LLM model files by authorized developers, ML engineers, and researchers during model training, fine-tuning, or experimentation. Approved AI/ML sandboxes and lab environments where model file creation is expected. Automated ML pipelines and workflows that generate or update model files as part of their normal operation. Third-party applications and services that manage or cache LLM model files for legitimate purposes.
Analyst notes
Known false positives: Legitimate creation of LLM model files by authorized developers, ML engineers, and researchers during model training, fine-tuning, or experimentation. Approved AI/ML sandboxes and lab environments where model file creation is expected. Automated ML pipelines and workflows that generate or update model files as part of their normal operation. Third-party applications and services that manage or cache LLM model files for legitimate purposes.