Analytics BIOC Informational

AI safeguards deletion attempt

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

Module:
Cortex Cloud
Licensed by:
Cloud Runtime Security (CRS)
Data source:
AWS Audit Log, Azure Audit Log
ATT&CK tactics: Defense Evasion (TA0005)
ATT&CK techniques: Impair Defenses (T1562)
Detector tags: Cloud AI Infrastructure Analytics
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.

Test period:
N/A (single event)
Deduplication:
5 Days
1 variation:
  • AI safeguards were successfully deleted Low (parent: Informational)