Elastic low stable kql
First Time GCP Vertex AI Inference by Caller from Source ASN
Detects the first time in 14 days that a Vertex AI caller (user or service account) runs model inference (GenerateContent, StreamGenerateContent, Predict, or RawPredict) from a source autonomous system (ASN). Stolen Google Cloud credentials, including exported service account keys and OAuth tokens, are used for LLMjacking from attacker infrastructure, which shows up as the victim identity calling models from a hosting provider, VPN, or residential proxy network it has never used before.
Detection Logic
data_stream.dataset:gcp_vertexai.auditlogs and event.action:(*PredictionService.GenerateContent* or *PredictionService.StreamGenerateContent* or *PredictionService.Predict* or *PredictionService.RawPredict*) and gcp.vertexai.audit.service_name:aiplatform.googleapis.com and client.user.email:* and source.as.number:* and gcp.vertexai.audit.status.code:(0 or not *) False Positives
- ⚠ Users working from a new network such as travel, a new ISP, or a mobile hotspot. Confirm the location with the user.
- ⚠ Service accounts whose workloads move between cloud providers, regions, or CI runners on different networks. Exclude these service accounts or pin their workloads to known networks.
Field Validations
Loading…
Comments (0)
Loading comments...