arXiv cs.AI· Alexandros Gkillas, Ioulia Kapsali, Christos Anagnostopoulos, Aris S. Lalos·· 3 小时前AI 评分28
LiDAR-SHIELD：面向 LiDAR 3D 感知模型的全 Docker 化对抗鲁棒性评估框架
LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models
AI 导读
研究者推出 LiDAR-SHIELD，一个全 Docker 化的统一对抗鲁棒性评估框架，用于测试 LiDAR 3D 感知模型。框架通过 /info、/forward、/gradient 三个 HTTP 端点接入任意模型，接入新模型或数据集只需一个 loader 函数或适配器。
正文 · 原文
Abstract: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.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39848 [cs.CV] |
| (or arXiv:2610.39848v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39848 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alexandros Gkillas [view email]
[v1]
Thu, 29 Oct 2026 11:27:53 UTC (148 KB)
来源：arXiv cs.AI · arxiv.org