AWS Bedrock High-Frequency Single-Model Inference API Probing

IMPORTANT: This documentation is no longer updated. Refer to Elastic's version policy and the latest documentation.

AWS Bedrock High-Frequency Single-Model Inference API Probing

Identifies an AWS principal performing a high volume of Amazon Bedrock inference API calls against a single model within a short window. Membership inference attacks require hundreds to thousands of statistically similar queries whose prompts and responses are intentionally content-benign, making guardrail- and content-based rules ineffective. This rule detects the high-frequency single-model probing pattern that precedes membership inference and related exfiltration via the inference API. It is a behavioral / volumetric precursor: it does not observe model confidence scores and a fixed call-count threshold only catches the loud variant, so paced, low-and-slow, or credential-distributed probing will evade it. Definitive membership inference detection requires ML anomaly analysis over per-entity inference-rate and response-distribution baselines.

Rule type: esql

Rule indices: None

Severity: medium

Risk score: 47

Runs every: 10m

Searches indices from: now-60m (Date Math format, see also Additional look-back time)

Maximum alerts per execution: 100

References:

Tags:

Domain: Cloud
Domain: LLM
Data Source: AWS
Data Source: Amazon Web Services
Data Source: AWS CloudTrail
Use Case: Threat Detection
Tactic: Exfiltration
Mitre Atlas: T0024
Mitre Atlas: T0024.000
Resources: Investigation Guide

Version: 2

Rule authors:

Elastic

Rule license: Elastic License v2

Investigation guide

edit

Triage and analysis

Investigating AWS Bedrock High-Frequency Single-Model Inference API Probing

Membership inference compares many samples against a model to infer whether specific records were present in training data. Because prompts and responses often appear benign, the actionable signal is frequently statistical: unusually high inference rates concentrated on one model from a single principal. AWS CloudTrail records the core Bedrock runtime operations (InvokeModel, InvokeModelWithResponseStream, Converse, ConverseStream) as management events, which are logged by default, so this probing phase is observable at the API layer even when Bedrock model invocation logging is disabled. CloudTrail does not capture the prompt body, so this rule is purely volumetric.

This rule is tuned to the loud case. Treat it as corroborating signal alongside other Bedrock alerts, not as conclusive membership inference detection.

Possible investigation steps

Identify the principal in aws.cloudtrail.user_identity.arn and the targeted model in the extracted Esql.model_id.
Determine whether the call volume exceeds the principal’s historical baseline for the same model.
Review companion Bedrock invocation logs, if enabled, for short prompts, repeated inputs, or low-variance responses that may indicate membership testing.
Inspect source.ip, user_agent.original, and recent IAM activity for signs of compromised credentials or unexpected automation.
Correlate with bulk output-extraction or guardrail alerts that may indicate a broader inference abuse campaign.

Response and remediation

Apply Bedrock service quotas and IAM least privilege for inference APIs while investigating.
Enable model invocation logging for content-level review if not already configured.
If abuse is confirmed, rotate access keys or disable the compromised principal.

Additional information

For further details on how Amazon Bedrock integrates with AWS CloudTrail to log control plane and data plane runtime operations, see the AWS Bedrock User Guide on CloudTrail Logging.
To explore the adversarial tactics, techniques, and case studies surrounding machine learning model data leakage, consult the MITRE ATLAS Exfiltration via Inferences (AML.T0024) documentation.

Setup

edit

Setup

This rule requires AWS CloudTrail management events for Amazon Bedrock and ingestion via the AWS integration (aws.cloudtrail data stream). The core Bedrock runtime operations are logged as management events by default; no Bedrock model invocation logging is required.

Rule query

edit

from logs-aws.cloudtrail-*

// Bedrock runtime inference APIs (CloudTrail management events, logged by default) used to probe at scale
| where
  event.provider == "bedrock.amazonaws.com"
  and event.action in (
    "InvokeModel",
    "Converse",
    "ConverseStream",
    "InvokeModelWithResponseStream"
  )
  and event.outcome == "success"
  and aws.cloudtrail.user_identity.arn IS NOT NULL
  and aws.cloudtrail.request_parameters IS NOT NULL

| grok aws.cloudtrail.request_parameters """modelId=(?<Esql.model_id>[^,}\]]+)"""
| where Esql.model_id IS NOT NULL

// preserve the grouping keys plus the ECS context fields collected via VALUES() below
| keep
  aws.cloudtrail.user_identity.arn,
  cloud.account.id,
  Esql.model_id,
  event.action,
  source.ip,
  user_agent.original,
  aws.cloudtrail.user_identity.type,
  aws.cloudtrail.user_identity.access_key_id,
  cloud.region,
  source.as.organization.name

// aggregate per principal + account + model, capturing analyst context with VALUES()
| stats
    Esql.inference_call_count = count(*),
    Esql.event_action_values = VALUES(event.action),
    Esql.source_ip_values = VALUES(source.ip),
    Esql.user_agent_original_values = VALUES(user_agent.original),
    Esql.aws_cloudtrail_user_identity_type_values = VALUES(aws.cloudtrail.user_identity.type),
    Esql.aws_cloudtrail_user_identity_access_key_id_values = VALUES(aws.cloudtrail.user_identity.access_key_id),
    Esql.cloud_region_values = VALUES(cloud.region),
    Esql.source_as_organization_name_values = VALUES(source.as.organization.name)
  by
    aws.cloudtrail.user_identity.arn,
    cloud.account.id,
    Esql.model_id

| where Esql.inference_call_count >= 500

| keep
  aws.cloudtrail.user_identity.arn,
  cloud.account.id,
  Esql.model_id,
  Esql.inference_call_count,
  Esql.event_action_values,
  Esql.source_ip_values,
  Esql.user_agent_original_values,
  Esql.aws_cloudtrail_user_identity_type_values,
  Esql.aws_cloudtrail_user_identity_access_key_id_values,
  Esql.cloud_region_values,
  Esql.source_as_organization_name_values

| sort Esql.inference_call_count desc

« AWS Lambda Layer Shared Externally AWS Bedrock Knowledge Base or RAG Data Source Tampering »