AI safeguards were modified

Analytics BIOC Informational

AI safeguards were modified

A cloud identity modified 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 changed safeguards filters and determine which AI models were affected. Investigate any unusual activity originating from the suspected identity.

Test period:: N/A (single event)
Deduplication:: 5 Days

2 variations:

Unusual modification of AI safeguards Low (parent: Informational)
AI safeguards were created or modified Informational