SOURCE-LINKED INTELLIGENCE

When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to be reused as off-the-shelf dynamics backbones for control, like pretrained encoders and language models are reused today. We show that this reuse opens a supply-chain backdoor: an adversary who controls only a released checkpoint can hijack the downstream controller, even though the victim trains and evaluates entirely on clean data and never sees the trigger. The attack encodes no explicit trigger-to-action rule. Instead, the poisoned model rout

Read original source ↗ Open in workspace

recordType

paper

region

Global