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 2406.00282cs.CVcs.CR
收藏

使用 Integrated Gradients 的对抗性 3D 虚拟补丁

Adversarial 3D Virtual Patches using Integrated Gradients

Imperial College London(帝国理工学院);University of Toronto(多伦多大学)

Chengzeng You, Zhongyuan Hau, Binbin Xu, Soteris Demetriou

AI总结:

本研究提出基于虚拟补丁的 3D 物体隐藏策略,并设计 Saliency-LiDAR 框架利用 Integrated Gradients 识别 LiDAR 物体关键区域,以更小的欺骗面积显著降低目标检测召回率。

摘要:

LiDAR 传感器被广泛应用于自动驾驶车辆以更好地感知环境。然而,先前的研究表明,LiDAR 信号可以被欺骗,从而向 3D 物体检测器隐藏真实物体。本研究探讨了通过一种基于虚拟补丁(VPs)的新型物体隐藏策略来减少所需欺骗面积的可行性。我们首先手动设计 VPs(MVPs),并表明聚焦 VP 的攻击可以实现与先前研究相似的成功率,但所需的欺骗面积仅为一小部分。然后我们设计了一个框架 Saliency-LiDAR(SALL),该框架可以使用 Integrated Gradients 识别 LiDAR 物体的关键区域。在关键区域上精心制作的 VPs(CVPs)与我们的基线相比,将物体检测召回率降低了至少 15%,同时对于平均尺寸的车辆,欺骗面积减少了约 50%。

英文摘要:

LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of reducing the required spoofing area through a novel object-hiding strategy based on virtual patches (VPs). We first manually design VPs (MVPs) and show that VP-focused attacks can achieve similar success rates with prior work but with a fraction of the required spoofing area. Then we design a framework Saliency-LiDAR (SALL), which can identify critical regions for LiDAR objects using Integrated Gradients. VPs crafted on critical regions (CVPs) reduce object detection recall by at least 15% compared to our baseline with an approximate 50% reduction in the spoofing area for vehicles of average size.

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。

↑