Get in touch
← Sentinel Explorer
↳ GitHub sourceConnector

AIShield

View on GitHub ↗Original file ↗

Description

[AIShield](https://www.boschaishield.com/) connector allows users to connect with AIShield custom defense mechanism logs with Microsoft Sentinel, allowing the creation of dynamic Dashboards, Workbooks, Notebooks and tailored Alerts to improve investigation and thwart attacks on AI systems. It gives users more insight into their organization's AI assets security posturing and improves their AI systems security operation capabilities.AIShield.GuArdIan analyzes the LLM generated content to identify and mitigate harmful content, safeguarding against legal, policy, role based, and usage based violations
Declared status
1
Declared author / publisher
Bosch

Declared sources

Metadata from the source file. No dependencies inferred from KQL.

Data types

AIShield_CL

Declared permissions

read and write permissions are required.
Workspace
Workspace
read permissions to shared keys for the workspace are required. [See the documentation to learn more about workspace keys](https://docs.microsoft.com/azure/azure-monitor/platform/agent-windows#obtain-workspace-id-and-key).
Keys
Workspace
Note
Users should have utilized AIShield SaaS offering to conduct vulnerability analysis and deployed custom defense mechanisms generated along with their AI asset. [**Click here**](https://azuremarketplace.microsoft.com/marketplace/apps/rbei.bgsw_aishield_product) to know more or get in touch.

Connector instructions

Content published in the repository. Refer to the original file for all parameters.

>**NOTE:** This data connector depends on a parser based on a Kusto Function to work as expected [**AIShield**](https://aka.ms/sentinel-boschaishield-parser) which is deployed with the Microsoft Sentinel Solution.
>**IMPORTANT:** Before deploying the AIShield Connector, have the Workspace ID and Workspace Primary Key (can be copied from the following).
Workspace ID
Primary Key

Related content

Links established from declared identifiers and solution manifests.

Analytics rules38
AIShield - Image classification AI Model Evasion high suspicious vulnerability detectionHighAIShield - Image classification AI Model Evasion low suspicious vulnerability detectionHighAIShield - Image classification AI Model extraction high suspicious vulnerability detectionHighAIShield - Image Segmentation AI Model extraction high suspicious vulnerability detectionHighAIShield - Natural language processing AI model extraction high suspicious vulnerability detectionHighAIShield - Tabular classification AI Model Evasion high suspicious vulnerability detectionHighAIShield - Tabular classification AI Model Evasion low suspicious vulnerability detectionMediumAIShield - Tabular classification AI Model extraction high suspicious vulnerability detectionHighAIShield - Timeseries Forecasting AI Model extraction high suspicious vulnerability detectionHighGuardian- Additional check JSON Policy Violation DetectionInformationalGuardian- Ban Topic Policy Violation DetectionMediumGuardian- BII Detection Policy Violation DetectionHighGuardian- Block Competitor Policy Violation DetectionLowGuardian- Blocks specific strings of text Policy Violation DetectionLowGuardian- Code Detection Policy Violation DetectionLowGuardian- Content Access Control Allowed List Policy Violation DetectionLowGuardian- Content Access Control Blocked List Policy Violation DetectionMediumGuardian- Content Safety Profanity Policy Violation DetectionLowGuardian- Content Safety Toxicity Policy Violation Detection.LowGuardian- Gender Bias Policy Violation DetectionLowGuardian- Input Output Relevance Policy Violation DetectionInformationalGuardian- Input Rate Limiter Policy Violation DetectionInformationalGuardian- Invisible Text Policy Violation DetectionLowGuardian- Language Detection Policy Violation DetectionInformationalGuardian- Malicious URL Policy Violation DetectionMediumGuardian- No LLM Output Policy Violation DetectionLowGuardian- Not Safe For Work Policy Violation DetectionLowGuardian- Privacy Protection PII Policy Violation DetectionHighGuardian- Racial Bias Policy Violation DetectionLowGuardian- Regex Policy Violation DetectionLowGuardian- Same Input/Output Language Detection Policy Violation DetectionInformationalGuardian- Secrets Policy Violation DetectionMediumGuardian- Security Integrity Checks Prompt Injection Policy Violation DetectionHighGuardian- Sentiment Policy Violation DetectionLowGuardian- Special PII Detection Policy Violation DetectionHighGuardian- Token Limit Policy Violation DetectionInformationalGuardian- URL Detection Policy Violation DetectionInformationalGuardian- URL Reachability Policy Violation DetectionInformational
Solutions1

Source provenance

GitHub

Displayed values come from files in Azure/Azure-Sentinel. They describe the published template, not your workspace configuration.

Source identifier
BoschAIShield
Additional source files 2Solutions/AIShield AI Security Monitoring/Data Connectors/AIShieldConnector.jsonsource ↗Solutions/AIShield AI Security Monitoring/Data/Solution_AIShield.jsonsolution-membership ↗
GSTEP / CATALOG TRACKING

Added to catalog : 16 Sept 2026 · 05:49 UTC
Last change observed : 16 Sept 2026 · 05:49 UTC

GSTEP sync dates, separate from the source content’s publication dates.