Metraipolis › archive › dc_fb32ca85ed82

Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study — arXiv:2609.26868

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26868
License (as archived): CC0-1.0
Archived: 2026-10-08T12:51:09.748Z
SHA-256 of the archived text: a9c746f5809bc20236fbc34ae0a2762d372a87d484ef036c85ef511339c456b9
Stable URL of this page: https://metraipolis.com/documento/dc_fb32ca85ed82

How to cite

Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study — arXiv:2609.26868 — arXiv (en), https://arxiv.org/abs/2609.26868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fb32ca85ed82 (Metraipolis archive dc_fb32ca85ed82, sha256 a9c746f5809bc20236fbc34ae0a2762d372a87d484ef036c85ef511339c456b9)

BibTeX

@misc{dcfb32ca85ed82,
  title = {Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study — arXiv:2609.26868},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fb32ca85ed82; sha256 a9c746f5809bc20236fbc34ae0a2762d372a87d484ef036c85ef511339c456b9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning-based models (e.g., visuomotor and Vision-Language-Action (VLA)) are increasingly explored for industrial robotic manipulation, where model predictions are directly translated into physical actions. This tight coupling between model behavior and physical execution makes hidden security vulnerabilities particularly consequential. While backdoor attacks have been widely studied in conventional AI models, their effects on deployed learning-based robotic arm manipulation systems remain less understood: a backdoored robot can behave normally during benign operation while inducing attacker-specified behaviors only when specific triggers are present, posing potentially serious risks in physical environments. In this work, we present a preliminary empirical security study of backdoor attacks and defenses in learning-based robotic manipulation on two real commercial industrial robotic arms (FANUC and xArm). We investigate whether a backdoor can reliably induce semantically incorrect manipulation behaviors while remaining stealthy under nominal task execution. We then develop an online defense pipeline that detects and neutralizes triggers at runtime, and compare its effectiveness against an offline fine-tuning defense. Beyond defense effectiveness, we further evaluate the computational latency and execution overhead introduced by the defense pipeline to assess its suitability for high-throughput industrial operation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.26868 — 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 2026-10-08T12:21:19.413Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).