AI 中文总结
AdvTiles是基于可学习瓦片的物理对抗伪装框架，通过ST Gumbel-Softmax和3D Gaussian Splatting优化，在保持自然外观的同时，使行人检测器平均攻击成功率达86.2%，优于现有方法，可制作为可穿戴服装在真实场景生效。
AI 中文摘要
针对行人检测器的物理对抗攻击已从局部补丁演变为全身纹理，但同时实现视觉自然性和强攻击效果仍具挑战性。现有视觉自然的方法通常将伪装纹理作为整体优化，限制了局部对抗模式及其空间排列的精细调整灵活性。为解决该问题，我们提出AdvTiles，一种基于可学习瓦片构建的物理对抗伪装框架，在保持自然伪装外观的同时实现强攻击性能。具体而言，我们使用直通（ST）Gumbel-Softmax估计器实现可微瓦片选择，支持瓦片模式与空间布局的联合优化，该设计提供对抗纹理生成的细粒度控制。为提升不同物理条件下的鲁棒性，我们进一步通过可微3D Gaussian Splatting渲染，结合视角、尺度、光照和背景的变化对伪装进行优化。在多个检测器上的大量实验表明，AdvTiles实现了86.2%的平均攻击成功率（ASR），优于现有最先进的攻击方法。我们还将优化后的伪装制作为可穿戴对抗服装，在不同距离、角度和背景的真实场景中验证了其有效性。
英文摘要
Physical adversarial attacks against person detectors have evolved from localized patches to full-body textures. However, achieving both visual naturalness and strong attack effectiveness remains challenging. Existing natural-looking methods typically optimize camouflage textures as a whole, limiting the flexibility to refine local adversarial patterns and their spatial arrangement. To address this issue, we propose AdvTiles, a physical adversarial camouflage framework built from learnable tiles, enabling strong attack performance while preserving a natural camouflage appearance. Specifically, we use a Straight-through (ST) Gumbel-Softmax estimator for differentiable tile selection, enabling joint optimization of tile patterns and spatial layouts. This design provides fine-grained control over adversarial texture generation. To improve robustness in diverse physical conditions, we further optimize the camouflage through differentiable 3D Gaussian Splatting rendering with variations in viewpoints, scales, illuminations and backgrounds. Extensive experiments across multiple detectors demonstrate that AdvTiles achieves an average ASR of 86.2%, outperforming existing state-of-the-art attack methods. We further fabricate the optimized camouflage into wearable adversarial clothing, validating its effectiveness in real-world scenarios across diverse distances, angles and backgrounds.
