Analytics Alerts

Browse the Cortex analytics alert reference.

Severity
Detection module
Data source
  • Unusual AI RAG Knowledge Base Modification Low Cloud

    AI knowledge base was modified by an identity that typically doesn't interact with knowledge bases. MITRE ATLAS Technique: AML.T0070 - RAG Poisoning. OWASP Top 10 LLM Technique: LLM04 - Data and Model Poisoning.

    Activation:
    14 Days
    Training:
    30 Days
    Test:
    N/A (single event)
    Deduplication:
    5 Days
    ATT&CK tactics: Impact (TA0040)
    ATT&CK techniques: Data Manipulation: Stored Data Manipulation (T1565.001)
    Required data: AWS Audit Log Gcp Audit Log
    Detector tags: Cloud AI Infrastructure Analytics
    Attacker's goals: Contaminating knowledge base, so that contextual information will be incorrect, biased or harmful.
    Investigative actions: Check the identity that modified the knowledge base. Check recent additions to the knowledge base.