AIShield - Timeseries Forecasting AI Model extraction high suspicious vulnerability detection

Back


Id	37118ef6-73b4-49aa-b13b-cdeeeea580df
Rulename	AIShield - Timeseries Forecasting AI Model extraction high suspicious vulnerability detection
Description	This alert creates an incident when Timeseries Forecasting 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/TimeSeriesForecastingModelExtractionHighSuspiciousVulnDetection.yaml
Version	1.0.4
Arm template	37118ef6-73b4-49aa-b13b-cdeeeea580df.json

KQL

AIShield
| where Message has 'Timeseries Forecasting 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

version: 1.0.4
tactics: []
alertDetailsOverride:
  alertDescriptionFormat: |
        This query detects Timeseries Forecasting 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 -Timeseries Forecasting AI Model extraction high suspicious vulnerability detected.
  alertTacticsColumnName: 
relevantTechniques: []
entityMappings:
- fieldMappings:
  - identifier: HostName
    columnName: HostName
  - identifier: NTDomain
    columnName: NTDomain
  entityType: Host
- fieldMappings:
  - identifier: Address
    columnName: SourceName
  entityType: IP
triggerThreshold: 0
name: AIShield - Timeseries Forecasting AI Model extraction high suspicious vulnerability detection
queryFrequency: 1h
triggerOperator: gt
eventGroupingSettings:
  aggregationKind: SingleAlert
kind: Scheduled
description: |
    'This alert creates an incident when Timeseries Forecasting AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.'
OriginalUri: https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/TimeSeriesForecastingModelExtractionHighSuspiciousVulnDetection.yaml
requiredDataConnectors:
- dataTypes:
  - AIShield
  connectorId: BoschAIShield
severity: High
query: |
  AIShield
  | where Message has 'Timeseries Forecasting AI Model Extraction Attack Identified'
  | where Severity =~ 'High'
  | where SuspiciousLevel =~ 'high suspicious attack'
  | extend NTDomain = tostring(split(Computer, '\\')[0]), HostName = tostring(split(Computer, '.')[0])  
queryPeriod: 1h
id: 37118ef6-73b4-49aa-b13b-cdeeeea580df
status: Available

ARM