AI safeguards deletion attempt

Cortex XSIAM Analytics Alert Reference by Alert name

Product
Cortex XSIAM
Last date published
2025-12-08
Category
Analytics Alert Reference
Index by
Alert name

Synopsis

Activation Period

14 Days

Training Period

30 Days

Test Period

N/A (single event)

Deduplication Period

5 Days

Required Data

  • Requires one of the following data sources:
    • AWS Audit Log
      OR
    • Azure Audit Log

Detection Modules

AIDR

Detector Tags

Cloud AI Infrastructure Analytics

ATT&CK Tactic

Defense Evasion (TA0005)

ATT&CK Technique

Impair Defenses (T1562)

Severity

Informational

Description

A cloud identity deleted AI safeguards.
MITRE ATLAS Technique: AML.T0015 - Evade ML Model.

Attacker's Goals

Evade model's restrictions and potentially accessing sensitive data or banned topics.

Investigative actions

  • Examine which AI models were affected.
  • Investigate any unusual activity originating from the suspected identity.

Variations

AI safeguards were successfully deleted

Synopsis

ATT&CK Tactic

Defense Evasion (TA0005)

ATT&CK Technique

Impair Defenses (T1562)

Severity

Low

Description

A cloud identity deleted AI safeguards.
MITRE ATLAS Technique: AML.T0015 - Evade ML Model.

Attacker's Goals

Evade model's restrictions and potentially accessing sensitive data or banned topics.

Investigative actions

  • Examine which AI models were affected.
  • Investigate any unusual activity originating from the suspected identity.