Our method utilizes animage-conditioned 3Dscene diffusion model to simultaneously denoise the 3D poses and geometries of all objects within the scene.

However, existing methods assume a reliable and unbiased forecasting environment, which isnot always available inthe wild. Inthis work, we investigate the vulnerability ofspatiotemporal trafficforecasting models andpropose apractical adversarial spatiotemporal attack framework.

These authors contributed equally to this work.

We also provide the lower and upper bounds ofadversarial transferability under certain conditions.