AIShield - Image Segmentation AI Model extraction high suspicious vulnerability detection

Back


Id	1ed02dcc-0bc9-465e-94b4-bd8969221602
Rulename	AIShield - Image Segmentation AI Model extraction high suspicious vulnerability detection
Description	This alert creates an incident when Image Segmentation AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.
Severity	High
Required data connectors	BoschAIShield
Kind	Scheduled
Query frequency	1h
Query period	1h
Trigger threshold	0
Trigger operator	gt
Source Uri	https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/ImageSegmentationModelExtractionHighSuspiciousVulnDetection.yaml
Version	1.0.4
Arm template	1ed02dcc-0bc9-465e-94b4-bd8969221602.json

KQL

AIShield
| where Message has 'Image Segmentation AI Model Extraction Attack Identified'
| where Severity =~ 'High'
| where SuspiciousLevel =~ 'high suspicious attack'
| extend NTDomain = tostring(split(Computer, '\\')[0]), HostName = tostring(split(Computer, '.')[0])

YAML

name: AIShield - Image Segmentation AI Model extraction high suspicious vulnerability detection
query: |
  AIShield
  | where Message has 'Image Segmentation AI Model Extraction Attack Identified'
  | where Severity =~ 'High'
  | where SuspiciousLevel =~ 'high suspicious attack'
  | extend NTDomain = tostring(split(Computer, '\\')[0]), HostName = tostring(split(Computer, '.')[0])  
entityMappings:
- entityType: Host
  fieldMappings:
  - columnName: HostName
    identifier: HostName
  - columnName: NTDomain
    identifier: NTDomain
- entityType: IP
  fieldMappings:
  - columnName: SourceName
    identifier: Address
queryPeriod: 1h
version: 1.0.4
tactics: []
triggerOperator: gt
kind: Scheduled
triggerThreshold: 0
OriginalUri: https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/ImageSegmentationModelExtractionHighSuspiciousVulnDetection.yaml
eventGroupingSettings:
  aggregationKind: SingleAlert
alertDetailsOverride:
  alertDescriptionFormat: |
        This query detects Image Segmentation AI Model extraction high suspicious, high severity alert from AIShield generated at {{TimeGenerated}}.\n\nPlease check the source for more information and investigate further.
  alertSeverityColumnName: Severity
  alertDisplayNameFormat: AIShield - Image Segmentation AI Model extraction high suspicious vulnerability detected.
  alertTacticsColumnName: 
relevantTechniques: []
id: 1ed02dcc-0bc9-465e-94b4-bd8969221602
severity: High
requiredDataConnectors:
- connectorId: BoschAIShield
  dataTypes:
  - AIShield
status: Available
description: |
    'This alert creates an incident when Image Segmentation AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.'
queryFrequency: 1h

ARM