AIShield - Image classification AI Model extraction high suspicious vulnerability detection

Back


Id	b4cc5396-2a34-45f5-a726-860e476edf15
Rulename	AIShield - Image classification AI Model extraction high suspicious vulnerability detection
Description	This alert creates an incident when Image classification 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/ImageClassficationModelExtractionHighSuspiciousVulnDetection.yaml
Version	1.0.4
Arm template	b4cc5396-2a34-45f5-a726-860e476edf15.json

KQL

AIShield
| where Message has 'Image Classification 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

relevantTechniques: []
OriginalUri: https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/ImageClassficationModelExtractionHighSuspiciousVulnDetection.yaml
eventGroupingSettings:
  aggregationKind: SingleAlert
query: |
  AIShield
  | where Message has 'Image Classification AI Model Extraction Attack Identified'
  | where Severity =~ 'High'
  | where SuspiciousLevel =~ 'high suspicious attack'
  | extend NTDomain = tostring(split(Computer, '\\')[0]), HostName = tostring(split(Computer, '.')[0])  
description: |
    'This alert creates an incident when Image classification AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.'
requiredDataConnectors:
- connectorId: BoschAIShield
  dataTypes:
  - AIShield
triggerOperator: gt
entityMappings:
- entityType: Host
  fieldMappings:
  - columnName: HostName
    identifier: HostName
  - columnName: NTDomain
    identifier: NTDomain
- entityType: IP
  fieldMappings:
  - columnName: SourceName
    identifier: Address
name: AIShield - Image classification AI Model extraction high suspicious vulnerability detection
queryPeriod: 1h
triggerThreshold: 0
id: b4cc5396-2a34-45f5-a726-860e476edf15
status: Available
kind: Scheduled
severity: High
queryFrequency: 1h
tactics: []
version: 1.0.4
alertDetailsOverride:
  alertSeverityColumnName: Severity
  alertTacticsColumnName: 
  alertDisplayNameFormat: AIShield - Image Classification AI Model extraction high suspicious vulnerability detected.
  alertDescriptionFormat: |
        This query detects Image Classification AI Model extraction high suspicious, high severity alert from AIShield generated at {{TimeGenerated}}.\n\nPlease check the source for more information and investigate further.

ARM