arxiv.org·2026/10/26
为什么重要 暴露多视图 BEV 感知的对抗鲁棒性风险，为自动驾驶安全测试与防御提供新基准和开源实现。
现代自动驾驶系统广泛采用基于多视图鸟瞰图（BEV）的 3D 感知模型，因为其性能优越。尽管取得成功，这些模型对对抗性伪装攻击的鲁棒性在很大程度上仍未被探索。现有伪装攻击主要针对单视图 2D 检测器，限制了其在多视图 3D 感知场景中的有效性。
为填补这一空白，我们提出 BEVCA，一种专为多视图 BEV 3D 感知定制的新型对抗性伪装生成框架。我们的框架将基于 BEV 特征的对抗损失与多视图神经渲染模块相结合，实现跨模型和任务的有效且可迁移的伪装攻击。
在数字和物理环境中的大量实验表明，BEVCA 优于最先进基线，并在真实世界条件下表现出强鲁棒性。我们的代码可在 https://github.com/WAVE-AT-IDEA/BEVCA 获取。
Modern autonomous driving systems widely adopt multi-view Bird's-Eye-View (BEV) based 3D perception models due to their superior performance.
Despite their success, the robustness of these models against adversarial camouflage attacks remains largely unexplored.
Existing camouflage attacks primarily target single-view 2D detectors, limiting their effectiveness in multi-view 3D perception settings.
To address this gap, we propose BEVCA, a novel adversarial camouflage generation framework tailored for multi-view BEV-based 3D perception.
Our framework integrates a BEV-feature-based adversarial loss with a multi-view neural rendering module, enabling effective and transferable camouflage attacks across different models and tasks.
Extensive experiments in both digital and physical settings demonstrate that BEVCA outperforms state-of-the-art baselines and exhibits strong robustness under real-world conditions.
Our code is available at https://github.com/WAVE-AT-IDEA/BEVCA.
原版排版与图表 · 手机无法内嵌时可在浏览器打开。PDF 插件内选文不能传给网页助手。