Metraipolis › archive › dc_604bf31cfe78

When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems — arXiv:2608.06830

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06830
License (as archived)
CC0-1.0
Archived
2026-10-19T09:53:02.226Z
SHA-256 of the archived text
afc3ee79c5e80c4c3faebcd8df59e7c695bdcb9b28bc3cf7e3001576690a5db3
Stable URL of this page
https://metraipolis.com/documento/dc_604bf31cfe78

How to cite

When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems — arXiv:2608.06830 — arXiv (en), https://arxiv.org/abs/2608.06830 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_604bf31cfe78 (Metraipolis archive dc_604bf31cfe78, sha256 afc3ee79c5e80c4c3faebcd8df59e7c695bdcb9b28bc3cf7e3001576690a5db3)
BibTeX
@misc{dc604bf31cfe78,
  title = {When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems — arXiv:2608.06830},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06830},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_604bf31cfe78; sha256 afc3ee79c5e80c4c3faebcd8df59e7c695bdcb9b28bc3cf7e3001576690a5db3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06830. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly used as high-level planners in embodied multi-robot systems, enabling robots to interpret natural language instructions and coordinate executable actions. Yet, this growing reliance on LLM planners also raises security concerns. Prior work has focused mainly on individual robots, while communication risks in multi-robot collaboration remain insufficiently understood. Existing multi-robot studies are further limited to preliminary analysis under the Decentralized Multi-agent System (DMAS) architecture, so it remains unclear whether these risks persist across other common communication architectures and how attacker access settings shape their propagation. To fill this gap, we formulate two communication attacks corresponding to distinct attacker access settings: the External Entry Point Attack and the Privileged In-System Attack. We evaluate both attacks across DMAS, HMAS-1, and HMAS-2 using three LLMs and five embodied multi-robot tasks. Results show that unsafe information can turn into unsafe actions across all three architectures: DMAS reaches a 96.7\% entry endorsement rate and a 100\% post endorsement activation rate, HMAS-1 reaches a 97.8\% unsafe action success rate, and HMAS-2 triggers 88.3\% of task defined unsafe action slots. To mitigate risks from trusted information flow, we introduce the Claim Provenance and Verification (CPV) Gate, which verifies communicated claims before downstream reuse and reduces the violation rate from 70.0\% to 36.6\%.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CR).
Categorie arXiv: Robotics (cs.RO) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.06830 — 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 2026-10-19T09:51:05.657Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).