Microsoft Sentinel Analytic Rules
cloudbrothers.infoAzure Sentinel RepoToggle Dark/Light/Auto modeToggle Dark/Light/Auto modeToggle Dark/Light/Auto modeBack to homepage

AIShield - Image classification AI Model extraction high suspicious vulnerability detection

Back
Idb4cc5396-2a34-45f5-a726-860e476edf15
RulenameAIShield - Image classification AI Model extraction high suspicious vulnerability detection
DescriptionThis alert creates an incident when Image classification AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.
SeverityHigh
Required data connectorsBoschAIShield
KindScheduled
Query frequency1h
Query period1h
Trigger threshold0
Trigger operatorgt
Source Urihttps://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/ImageClassficationModelExtractionHighSuspiciousVulnDetection.yaml
Version1.0.4
Arm templateb4cc5396-2a34-45f5-a726-860e476edf15.json
Deploy To Azure
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])
status: Available
OriginalUri: https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/ImageClassficationModelExtractionHighSuspiciousVulnDetection.yaml
alertDetailsOverride:
  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.
  alertTacticsColumnName: 
  alertSeverityColumnName: Severity
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])  
requiredDataConnectors:
- dataTypes:
  - AIShield
  connectorId: BoschAIShield
tactics: []
name: AIShield - Image classification AI Model extraction high suspicious vulnerability detection
relevantTechniques: []
severity: High
entityMappings:
- fieldMappings:
  - identifier: HostName
    columnName: HostName
  - identifier: NTDomain
    columnName: NTDomain
  entityType: Host
- fieldMappings:
  - identifier: Address
    columnName: SourceName
  entityType: IP
kind: Scheduled
queryFrequency: 1h
description: |
    'This alert creates an incident when Image classification AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.'
eventGroupingSettings:
  aggregationKind: SingleAlert
triggerThreshold: 0
triggerOperator: gt
version: 1.0.4
queryPeriod: 1h
id: b4cc5396-2a34-45f5-a726-860e476edf15