| title | BadWorld: Adversarial Attacks on World Models |
|---|---|
| authors | Linghui Shen, Mingyue Cui, Xingyi Yang |
| date | 2026-06-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.16519 |
| affiliation | The Hong Kong Polytechnic University |
| upvotes | 16 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | World models |
| abstract | Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attackers lack ground-truth future videos and cannot predict subsequent user controls. We introduce BadWorld, a label-free adversarial framework tailored for autoregressive VWMs that systematically overcomes both constraints. First, to bypass the need for future supervision, we propose a self-supervised velocity attack that directly disrupts the early denoising dynamics of the model. Second, to ensure the attack generalizes across unpredictable user actions, we formulate a trajectory-adaptive bi-level optimization that actively mines hard control sequences to forge control-agnostic perturbations. Evaluated on representative VWMs with continuous and discrete controls, BadWorld exposes severe structural fragility. Visually indistinguishable adversarial images reliably trigger catastrophic degradation in future rollouts, leading to incomplete denoising, structural collapse, and control inconsistency. These findings reveal critical risks for deploying VWMs in safety-critical systems while highlighting a practical mechanism for privacy protection. |
cite
@misc{shen2026badworld,
title={BadWorld: Adversarial Attacks on World Models},
author={Linghui Shen and Mingyue Cui and Xingyi Yang},
year={2026},
eprint={2606.16519},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.16519}
}