Hugging Face Trending Papers

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

Read the original on Hugging Face Trending Papers →

World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedback into physical action.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 9

Targeting World Models to Compromise Robot Learning Pipelines

arXiv:2606. 09499v1 Announce Type: cross Abstract: 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.

By Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud, Christopher Amato, Alina Oprea, Eugene Bagdasarian
arXiv AI
Aug 7

DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

arXiv:2608. 05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services.

By Wenhao Lin, Chenyu Yu, Xingwei Lin, Sicong Cao, Xiang Chen, Lei Xue, Le Yu, Letian Sha, Chunming Wu