Metraipolis › archive › dc_da00baf0aeea
Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation — arXiv:2608.16843
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16843
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T23:08:18.009Z
- SHA-256 of the archived text
f9104a4b2f34217a320cda9bde0ed6cc937f2823b5ab84aef3b6325d9492d924- Stable URL of this page
https://metraipolis.com/documento/dc_da00baf0aeea
How to cite
Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation — arXiv:2608.16843 — arXiv (en), https://arxiv.org/abs/2608.16843 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da00baf0aeea (Metraipolis archive dc_da00baf0aeea, sha256 f9104a4b2f34217a320cda9bde0ed6cc937f2823b5ab84aef3b6325d9492d924)
BibTeX
@misc{dcda00baf0aeea,
title = {Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation — arXiv:2608.16843},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16843},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da00baf0aeea; sha256 f9104a4b2f34217a320cda9bde0ed6cc937f2823b5ab84aef3b6325d9492d924},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16843. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a trust-boundary-centric survey of foundation-model-powered embodied-agent security. Using a first-compromised-trust-boundary principle, we separate attack surface from attack mechanism and organize the system into five layers and twelve attack surfaces spanning the model supply chain, user instructions, context and memory, physical semantic environments, multimodal perception, world state, internal reasoning, task planning, action interfaces, middleware, multi-agent communication, and execution control. Based on 58 attack records and 61 defense records collected through August 15, 2026, we analyze representative attacks, cross-layer propagation, defense placement, and evaluation practices. Our quantitative analysis shows that attack research is concentrated on multimodal perception and action interfaces, while defenses are especially concentrated on action-level and runtime protection. Context and long-term memory, middleware and networking, world-state integrity, and multi-agent trust remain comparatively underexplored. We conclude with open challenges in state provenance, compositional defenses, long-horizon attack propagation, physical realizability, Byzantine multi-robot behavior, and unified closed-loop evaluation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.16843 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T23:01:50.399Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).