Detect suspicious processnames using pretrained model in DSDL
THIS IS A EXPERIMENTAL DETECTION
This detection has been marked experimental by the Splunk Threat Research team. This means we have not been able to test, simulate, or build datasets for this detection. Use at your own risk. This analytic is NOT supported.
Description
The following analytic identifies suspicious process names using a pre-trained Deep Learning model. It leverages Endpoint Detection and Response (EDR) telemetry to analyze process names and predict their likelihood of being malicious. The model, a character-level Recurrent Neural Network (RNN), classifies process names as benign or suspicious based on a threshold score of 0.5. This detection is significant as it helps identify malware, such as TrickBot, which often uses randomly generated filenames to evade detection. If confirmed malicious, this activity could indicate the presence of malware capable of propagating across the network and executing harmful actions.
- Type: Anomaly
- Product: Splunk Enterprise, Splunk Enterprise Security, Splunk Cloud
- Datamodel: Endpoint
- Last Updated: 2024-05-27
- Author: Abhinav Mishra, Kumar Sharad and Namratha Sreekanta, Splunk
- ID: a15f8977-ad7d-4669-92ef-b59b97219bf5
Annotations
Kill Chain Phase
- Installation
NIST
- DE.AE
CIS20
- CIS 10
CVE
Search
1
2
3
4
5
6
7
8
9
10
| tstats `security_content_summariesonly` count min(_time) as firstTime max(_time) as lastTime from datamodel=Endpoint.Processes by Processes.process_name Processes.parent_process_name Processes.process Processes.user Processes.dest
| `drop_dm_object_name(Processes)`
| rename process_name as text
| fields text, parent_process_name, process, user, dest
| apply detect_suspicious_processnames_using_pretrained_model_in_dsdl
| rename predicted_label as is_suspicious_score
| rename text as process_name
| where is_suspicious_score > 0.5
| `detect_suspicious_processnames_using_pretrained_model_in_dsdl_filter`
Macros
The SPL above uses the following Macros:
detect_suspicious_processnames_using_pretrained_model_in_dsdl_filter is a empty macro by default. It allows the user to filter out any results (false positives) without editing the SPL.
Required fields
List of fields required to use this analytic.
- _time
- Processes.process
- Processes.parent_process_name
- Processes.process_name
- Processes.parent_process
- Processes.user
- Processes.dest
How To Implement
The detection is based on data that originates from Endpoint Detection and Response (EDR) agents. These agents are designed to provide security-related telemetry from the endpoints where the agent is installed. To implement this search, you must ingest logs that contain the process GUID, process name, and parent process. Additionally, you must ingest complete command-line executions. These 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 Processes
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
False positives may be present if a suspicious processname is similar to a benign processname.
Associated Analytic Story
RBA
Risk Score | Impact | Confidence | Message |
---|---|---|---|
45.0 | 50 | 90 | The process $process$ is running from an unusual place by $user$ on $dest$ with a processname that appears to be randomly generated. |
The Risk Score is calculated by the following formula: Risk Score = (Impact * Confidence/100). Initial Confidence and Impact is set by the analytic author.
Reference
- https://www.cisa.gov/uscert/ncas/alerts/aa20-302a
- https://www.splunk.com/en_us/blog/security/random-words-on-entropy-and-dns.html
Test Dataset
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 | version: 2