Metraipolis › archive › dc_da91ffa16b67

Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems — arXiv:2609.26184

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26184
License (as archived)
CC0-1.0
Archived
2026-10-08T13:46:59.985Z
SHA-256 of the archived text
572653a2959308f4d2127a2932532112f4a1163051584c69bdf572ca1c51840e
Stable URL of this page
https://metraipolis.com/documento/dc_da91ffa16b67

How to cite

Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems — arXiv:2609.26184 — arXiv (en), https://arxiv.org/abs/2609.26184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da91ffa16b67 (Metraipolis archive dc_da91ffa16b67, sha256 572653a2959308f4d2127a2932532112f4a1163051584c69bdf572ca1c51840e)
BibTeX
@misc{dcda91ffa16b67,
  title = {Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems — arXiv:2609.26184},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26184},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da91ffa16b67; sha256 572653a2959308f4d2127a2932532112f4a1163051584c69bdf572ca1c51840e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning. While this paradigm shift accelerates progress, it also introduces novel security risks that remain largely unexplored. Current research into LLM backdoors has focused on attacks triggered by external stimuli, such as specific words, visual objects, or environmental states. These attacks, while potent, overlook a more insidious class of vulnerability where the trigger is internal to the agent's own operational logic. This paper presents the first comprehensive study of history-based backdoor attacks on LLM-powered robotic systems. We demonstrate that an attacker can embed a stealthy backdoor into an LLM-based robot controller by manipulating its instructions. This backdoor is triggered not by an external cue, but by a specific, rare sequence of the robot's own past actions. It remains dormant during normal operation, preserving the robot's utility, but can be activated to induce a malicious behavior, such as a complete stop or a collision. Our experiments, conducted in a simulated environment with a variety of robots and LLMs, show that this history-based attack is highly effective, achieving a near-perfect attack success rate while remaining exceptionally difficult to detect. These findings reveal a critical and previously unaddressed vulnerability in autonomous systems and underscore the urgent need for security measures that account for an agent's internal state.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.26184 — 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 2026-10-08T13:18:38.293Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).