Skip to content

Compute

Local and Dreadnode-hosted compute modes for AI red teaming operations.

AI red teaming attacks can execute in two modes: locally on your machine or in Dreadnode-hosted sandboxes. Both modes send results to the platform for analytics and reporting.

When you launch the TUI or run CLI commands locally, all attack execution happens on your machine:

Terminal window
dn --capability ai-red-teaming --model openai/gpt-4o

In local mode:

  • Attacks execute on your local machine using your local Python environment
  • You provide API keys for the target, attacker, and judge models via environment variables (see Prerequisites)
  • Results, traces, and findings are uploaded to the Dreadnode platform automatically
  • You can see the attack overview, findings, analytics, and compliance mapping in the platform dashboard
  • You only pay for storage of the data in the platform and inference costs if you use Dreadnode-hosted models (dn prefix). There is no compute charge for local execution.

This is the simplest way to get started. No sandbox provisioning, no runtime configuration. Just set your API keys and run.

When you attach to a Dreadnode runtime, attacks execute inside isolated Dreadnode sandboxes:

Terminal window
dn --capability ai-red-teaming --model openai/gpt-4o --runtime-server <runtime-url>

In Dreadnode-hosted mode:

  • Attacks execute in isolated sandbox containers managed by Dreadnode
  • API keys are configured as Secrets in the platform and injected into sandboxes automatically
  • Model calls route through the platform’s model proxy with usage tracking
  • Sandboxes are provisioned automatically when you start an assessment
  • Dreadnode charges for sandbox compute time in addition to model inference and storage
  • Usage is visible in Credits

Use Dreadnode-hosted compute when you need:

  • Isolation from your local environment
  • Centrally managed secrets and API keys
  • Consistent execution environment across team members
  • Long-running campaigns that should not depend on your local machine staying online
Terminal window
dn airt sandbox <assessment-id>
Local modeDreadnode-hosted
Launchdn --capability ai-red-teaming --model openai/gpt-4odn --capability ai-red-teaming --model openai/gpt-4o --runtime-server <url>
API keysEnvironment variables on your machinePlatform Secrets
ExecutionYour local machineDreadnode sandboxes
Status barShows localShows remote
Platform resultsYes, uploaded automaticallyYes, streamed in real time
CostStorage + inference (if using dn models)Storage + inference + sandbox compute
Best forGetting started, development, quick testsProduction operations, team use, long campaigns