Targets

A target is the system under test — the model or service an attack sends its (possibly transformed) prompt to and reads a response from. Dreadnode probes any target that accepts input and returns output, whether it is a hosted model id, a self-hosted endpoint, or a cloud-managed deployment.

Platform-provided vs. bring-your-own

There are two ways to point an attack at a model, and they have very different setup:

	Platform-provided	Bring-your-own
What	Models the platform hosts/routes — dn/... ids	Your own deployment or a provider account you hold
Examples	dn/claude-sonnet-4-6, dn/gpt-5.4-mini, dn/glm-5.2	your AWS SageMaker endpoint, your Bedrock/Nova, Azure AI, Vertex AI, a provider key (openai/, gemini/)
Setup	None — no keys, no URLs, no IAM	Your credentials + (for cloud) IAM/model-access
Billing	Metered to your Dreadnode account	Billed by your cloud/provider account

If a model id starts with dn/, it’s platform-provided: just use it — the gateway holds the keys and bills your account. Everything else on this page is bring-your-own: you supply the endpoint and credentials.

Note

Speech-to-speech is bring-your-own today. Amazon Nova Sonic streams over a Bedrock bidirectional connection, which the platform’s chat gateway doesn’t proxy yet — so Nova runs against your AWS account, not dn/. Platform-provided S2S (no AWS setup) is planned; until then, see AWS Nova Sonic.

For arbitrary HTTP APIs see Custom Endpoints.

Target transports

Transport	Use for	How auth works
Model id	Hosted/provider models (openai/…, anthropic/…, gemini/…), Azure OpenAI / Foundry (azure/…), and platform dn/… models	Provider API key (Azure: AZURE_API_KEY/_BASE/_VERSION), or the platform LLM gateway for dn/…
HTTP + SigV4	AWS SageMaker real-time & serverless endpoints	AWS SigV4 request signing (IAM)
HTTP + key / bearer / cloud identity	Azure AI (managed identity), Vertex AI, custom REST APIs	API-key header, bearer token, Azure AD / GCP ADC
Streaming	Amazon Nova Sonic speech-to-speech (Bedrock bidirectional stream)	AWS IAM credential chain

From the SDK you build a declarative TargetSpec and turn it into a runnable @task with build_target(...); from the TUI you describe the target in natural language and the agent wires it up.

from dreadnode.airt.targets import build_target, TargetSpec, TargetAuth

# HTTP + SigV4 (SageMaker), messages-style multimodal endpoint
target = build_target(TargetSpec(
    endpoint="https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/my-endpoint/invocations",
    auth=TargetAuth(type="aws_sigv4", region="us-west-2", service="sagemaker"),
    request_template='{"messages":[{"role":"user","content":[{"type":"text","text":"{prompt}"}]}]}',
    response_text_path="$.choices[0].message.content",
))

The request template supports {prompt}, {image_b64}, {audio_b64}, and {video_b64} placeholders, so a single spec can carry multimodal input to the endpoint.

Note

Whatever the transport, the attack, transforms, and scoring are identical — only the target wiring changes. That means you can run the same multimodal probe against a hosted model, a SageMaker endpoint, or Nova Sonic and compare results side by side.

Cloud & custom targets

AWS SageMaker Probe a real-time or serverless SageMaker endpoint (incl. multimodal vision models) via SigV4.

AWS Nova Sonic Probe Amazon Nova Sonic speech-to-speech over the Bedrock bidirectional stream.

Azure AI Foundry Probe multimodal (vision + audio) Azure OpenAI / Foundry deployments — just set your Azure keys and use azure/.

Multi-Agent Systems Red team a multi-agent system deployed in your own cloud (Azure or AWS) with ATLAS — per-agent tool calls in findings.

Custom Endpoints Azure AI, Vertex AI, agent loops, RAG pipelines, and arbitrary REST APIs.

Multimodal Red Teaming Image / audio / video probing and the transform catalog, applied to any target.