arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.39848cs.CVcs.AI
收藏

LiDAR-SHIELD:用于基于激光雷达的3D感知模型的完全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

Industrial Systems Institute, Athena Research Center(雅典娜研究中心工业系统研究所)

Alexandros Gkillas, Ioulia Kapsali, Christos Anagnostopoulos, Aris S. Lalos

AI总结:

提出完全Docker化的LiDARSHIELD框架,通过三个HTTP端点简化模型接入,集成多种对抗攻击,用于评估基于激光雷达的3D感知模型的鲁棒性,暴露其漏洞。

摘要:

基于激光雷达的3D感知是自动驾驶和机器人技术的基础,但要安全部署这些模型,需在实际应用前针对对抗输入进行压力测试。尽管存在最先进的对抗攻击方法,但其实现通常分散在各个代码仓库中,每个仓库都与特定架构或任务绑定,且需要手动重建环境和特定于模型的集成代码。我们提出LiDARSHIELD,这是一个统一且完全Docker化的框架,它颠覆了这一工作流程:不是在工具包内部署目标模型,而是LiDARSHIELD通过三个轻量级HTTP端点(即/info、/forward和/gradient)公开任何模型。因此,连接新模型或数据集仅需一个加载器函数或适配器。该框架通过相同的引擎-服务协议支持3D语义分割和3D目标检测,集成了一套针对任务的最先进攻击方法,包括用于分割的PGD和Square Attack,以及用于检测的点扰动、点移除、点注入和LiDAttack。这能够系统地暴露异构激光雷达主干的极端情况和漏洞。LiDAR-Shield代码库可在此https URL获取。

英文摘要:

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 https://github.com/alexandrosgk/LiDAR-shield.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑