GCP Vertex AI Repeated Assistant Refusals

Last updated 18 days ago on 2026-11-03
Created 2 months ago on 2026-10-02

About

Detects three or more Vertex AI GenerateContent replies in 60 minutes whose assistant text indicates a refusal (cannot fulfill/assist/help/answer, unable to assist, decline the request, against my guidelines, and similar), aggregated by project and model. Prompt-response logs lack a stable caller identity, so this is a project-wide refusal burst signal — pivot to auditlogs for principal/IP attribution.
Tags
Domain: GenAIDomain: CloudData Source: GCP Vertex AIData Source: GCPData Source: Google Cloud PlatformPlatform: GCPService: GCP Vertex AIUse Case: Policy ViolationUse Case: Threat DetectionTactic: Defense EvasionThreat: Unauthorized AI UsageRule Type: ES|QLLanguage: esql
Severity
high
Risk Score
73
False Positive Examples
Approved red-team suites that intentionally elicit refusals. Exclude those models or raise the threshold.
License
Elastic License v2(external, opens in a new tab or window)

Definition

Integration Pack
Prebuilt Security Detection Rules
Related Integrations

gcp_vertexai(external, opens in a new tab or window)

Query
text code block:
from logs-gcp_vertexai.prompt_response_logs-* | where data_stream.dataset == "gcp_vertexai.prompt_response_logs" and MV_CONTAINS(gcp.vertexai.prompt_response_logs.full_response.candidates.finish_reason, "STOP") | eval response_text = to_lower(coalesce(mv_concat(gcp.vertexai.prompt_response_logs.full_response.candidates.content.parts.text, " "), "")) | where response_text like "*cannot fulfill*" or response_text like "*cannot assist*" or response_text like "*can't assist*" or response_text like "*can't help*" or response_text like "*cannot help*" or response_text like "*i cannot provide*" or response_text like "*i can't provide*" or response_text like "*i will not provide*" or response_text like "*i cannot answer*" or response_text like "*i can't answer*" or response_text like "*unable to provide*" or response_text like "*unable to assist*" or response_text like "*unable to fulfill*" or response_text like "*not able to help*" or response_text like "*not able to provide*" or response_text like "*must decline*" or response_text like "*respectfully decline*" or response_text like "*decline this request*" or response_text like "*decline that request*" or response_text like "*cannot disclose*" or response_text like "*can't disclose*" or response_text like "*against my guidelines*" or response_text like "*that violates my guidelines*" | stats Esql.event_count = count(*), Esql.timestamp_first_seen = min(@timestamp), Esql.timestamp_last_seen = max(@timestamp), Esql.prompt_values = values(gcp.vertexai.prompt_response_logs.full_request.contents.parts.text), Esql.response_values = values(gcp.vertexai.prompt_response_logs.full_response.candidates.content.parts.text) by gcp.vertexai.prompt_response_logs.model, cloud.project.id | where Esql.event_count >= 3 | keep gcp.vertexai.prompt_response_logs.model, cloud.project.id, Esql.event_count, Esql.timestamp_first_seen, Esql.timestamp_last_seen, Esql.prompt_values, Esql.response_values

Install detection rules in Elastic Security

Detect GCP Vertex AI Repeated Assistant Refusals in the Elastic Security detection engine by installing this rule into your Elastic Stack.

To setup this rule, check out the installation guide for Prebuilt Security Detection Rules(external, opens in a new tab or window).