Multimodal attacks

Multimodal Attack

Transform-based probing across vision, audio, and text modalities. Applies the transform catalog to multimodal inputs (images, audio, or mixed) before scoring the model’s response.

from dreadnode.airt import multimodal_attack

When to use: Testing multimodal models that accept images, audio, or mixed inputs.

Tip

For the end-to-end multimodal workflow (media inventory, modality-typed transforms, and reviewing the multimodal message parts of each finding), see Multimodal Red Teaming.