AIShield - Natural language processing AI model extraction high suspicious vulnerability detection

Back


Id	4ec55816-e07b-45fc-b89e-917c93906540
Rulename	AIShield - Natural language processing AI model extraction high suspicious vulnerability detection
Description	This alert creates an incident when Natural language processing 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/NaturalLanguageProcessingModelExtractionHighSuspiciousVulDetection.yaml
Version	1.0.1
Arm template	4ec55816-e07b-45fc-b89e-917c93906540.json

KQL

AIShield
| where Message has 'Natural Language Processing 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

id: 4ec55816-e07b-45fc-b89e-917c93906540
alertDetailsOverride:
  alertDisplayNameFormat: AIShield - Natural language processing AI model extraction high suspicious vulnerability detected
  alertSeverityColumnName: Severity
  alertDescriptionFormat: |
        This query detects Natural language processing 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: 
triggerThreshold: 0
description: |
    This alert creates an incident when Natural language processing AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.'
requiredDataConnectors:
- connectorId: BoschAIShield
  dataTypes:
  - AIShield
queryPeriod: 1h
version: 1.0.1
severity: High
tactics: []
queryFrequency: 1h
kind: Scheduled
eventGroupingSettings:
  aggregationKind: SingleAlert
entityMappings:
- entityType: Host
  fieldMappings:
  - columnName: HostName
    identifier: HostName
  - columnName: NTDomain
    identifier: NTDomain
- entityType: IP
  fieldMappings:
  - columnName: SourceName
    identifier: Address
name: AIShield - Natural language processing AI model extraction high suspicious vulnerability detection
relevantTechniques: []
triggerOperator: gt
query: |
  AIShield
  | where Message has 'Natural Language Processing 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/NaturalLanguageProcessingModelExtractionHighSuspiciousVulDetection.yaml

ARM