Potential Abuse of Resources by High Token Count and Large Response Sizes

edit

Potential Abuse of Resources by High Token Count and Large Response Sizes

edit

Detects potential resource exhaustion or data breach attempts by monitoring for users who consistently generate high input token counts, submit numerous requests, and receive large responses. This behavior could indicate an attempt to overload the system or extract an unusually large amount of data, possibly revealing sensitive information or causing service disruptions.

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: LLM
  • Data Source: AWS Bedrock
  • Data Source: Amazon Web Services
  • Data Source: AWS S3
  • Use Case: Potential Overload
  • Use Case: Resource Exhaustion
  • Mitre Atlas: LLM04

Version: 1

Rule authors:

  • Elastic

Rule license: Elastic License v2

Setup

edit

Setup

This rule requires that guardrails are configured in AWS Bedrock. For more information, see the AWS Bedrock documentation:

https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-create.html

Rule query

edit
from logs-aws_bedrock.invocation-*
| stats max_tokens = max(gen_ai.usage.prompt_tokens),
         total_requests = count(*),
         avg_response_size = avg(gen_ai.usage.completion_tokens)
  by user.id
// tokens count depends on specific LLM, as is related to how embeddings are generated.
| where max_tokens > 5000 and total_requests > 10 and avg_response_size > 500
| eval risk_factor = (max_tokens / 1000) * total_requests * (avg_response_size / 500)
| where risk_factor > 10
| sort risk_factor desc