RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents

Abstract

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural language commands in diverse environments. Previous research has introduced jailbreak attacks and defenses for embodied AI. Their evaluations, however, rely on ad-hoc datasets, limited metrics, and emphasize attack success while neglecting the trade-off between

Categories

Framework mappings

Suggested from the entry's categories.

@misc{yeke2026robojailbench,
  title = {{RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents}},
  author = {Doguhuan Yeke and Yanming Zhou and Leo Y. Lin and Hongyu Cai and Antonio Bianchi and Z. Berkay Celik},
  year = {2026},
  month = may,
  eprint = {2605.19328},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.19328}
}