Metraipolis › archive › dc_7e2fb97daff7

LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models — arXiv:2610.39848

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39848
License (as archived): CC0-1.0
Archived: 2026-10-31T06:13:27.350Z
SHA-256 of the archived text: c366024e49b0e9859cdc799351b9b72edb9922edb1b633180e3f5a73df8fb00f
Stable URL of this page: https://metraipolis.com/documento/dc_7e2fb97daff7

How to cite

LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models — arXiv:2610.39848 — arXiv (en), https://arxiv.org/abs/2610.39848 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e2fb97daff7 (Metraipolis archive dc_7e2fb97daff7, sha256 c366024e49b0e9859cdc799351b9b72edb9922edb1b633180e3f5a73df8fb00f)

BibTeX

@misc{dc7e2fb97daff7,
  title = {LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models — arXiv:2610.39848},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39848},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e2fb97daff7; sha256 c366024e49b0e9859cdc799351b9b72edb9922edb1b633180e3f5a73df8fb00f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39848. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LiDAR-based 3D perception underpins autonomous driving and robotics, yet deploying these models safely requires stress-testing them against adversarial inputs before real-world use. Although state-of-the-art adversarial attacks exist, their implementations are often fragmented across individual repositories, each tied to a specific architecture or task and requiring manual environment reconstruction and model-specific integration code. We present LIDARSHIELD, a unified and fully Dockerized framework that reverses this workflow: rather than installing the target model inside the toolkit, LIDARSHIELD exposes any model through three lightweight HTTP endpoints, namely /info, /forward, and /gradient As a result, connecting a new model or dataset requires only a single loader function or adapter. The framework supports both 3D semantic segmentation and 3D object detection through the same engine-service protocol, integrating a task-aware suite of state-of-the-art attacks, including PGD and Square Attack for segmentation, and point perturbation, point removal, point injection, and LiDAttack for detection. This enables systematic exposure of corner cases and vulnerabilities across heterogeneous LiDAR backbones. The LiDAR-Shield codebase is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.39848 — 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 2026-10-31T06:07:08.739Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).