LoFP / policy administrators, ml platform engineers, or infrastructure-as-code pipelines may legitimately update or remove automated reasoning policies during model governance changes, policy tuning, or environment teardown. verify that the user identity, source ip, and user agent correspond to an approved change and that a corresponding change request exists. known automation roles can be exempted if they generate recurring noise.

Techniques

• T1562

Sample rules

AWS Bedrock Automated Reasoning Safety Policy Tampering

• source: elastic
• technicques:
  • T1562

Description

Detects deletion or modification of AWS Bedrock Automated Reasoning policies via the DeleteAutomatedReasoningPolicy, UpdateAutomatedReasoningPolicy, or UpdateAutomatedReasoningPolicyAnnotations CloudTrail actions. Automated Reasoning policies are a Bedrock safety and validation control that constrains model outputs against formal rules. An adversary who deletes a policy or alters the policy definition or its annotations weakens an enforced output-validation defense, potentially allowing unsafe or non-compliant model responses to pass unchecked. Benign build, test-workflow, and test-case CRUD operations are intentionally excluded as they have no coherent abuse path.

Detection logic

data_stream.dataset: "aws.cloudtrail" and
    event.provider: "bedrock.amazonaws.com" and
    event.action: (
        "DeleteAutomatedReasoningPolicy" or
        "UpdateAutomatedReasoningPolicy" or
        "UpdateAutomatedReasoningPolicyAnnotations"
    ) and event.outcome:success