2606.09499v1 Jun 08, 2026 cs.RO

Targeting World Models to Compromise Robot Learning Pipelines

Eugene Bagdasarian
Eugene Bagdasarian
Citations: 54
h-index: 4
Ethan Rathbun
Ethan Rathbun
Citations: 125
h-index: 5
A. Agha
A. Agha
Citations: 55
h-index: 5
S. Mahmud
S. Mahmud
Citations: 51
h-index: 4
Christopher Amato
Christopher Amato
Citations: 26
h-index: 2
Alina Oprea
Alina Oprea
Citations: 57
h-index: 3

World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline. While highly practical, in this work we demonstrate that world models introduce a uniquely stealthy and effective data poisoning entry point into the robot learning supply chain that can result in the deployment of unsafe or otherwise compromised robotic policies despite training on seemingly safe ground truth training data. In contrast to traditional data poisoning techniques which directly implant dangerous trajectories into sold or uploaded datasets, our novel attack methods inject malicious prompts or compromising transition dynamics into visibly safe teleoperated datasets which are only activated once fed through a world model as input. This can result in the generation of synthetic, dangerous robot training trajectories and subsequently unsafe or compromised robot policies. We demonstrate the effectiveness of our attacks against both state of the art action conditioned and text conditioned world models, showing a full end-to-end backdoor on a downstream DRL policy and a proof-of-concept for the VLA setting. Overall these findings necessitate research into more secure world models and reevaluating their position within the robot learning supply chain.

0 Citations
0 Influential
2.5 Altmetric
12.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!