Abstract: World action models (WAMs) predict future videos and actions with one backbone, and their imagined future is often seen as a safety signal. We introduce SteerTrace, a targeted universal attack on WAMs that also traces its effect inside the model. One $\ell_\infty$-bounded (4/255) perturbation per model, shared across frames, tasks, and camera
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
SteerTrace: Tracing How Target Attacks Steer World Action Models
