通过可学习纹理与透明度的物理贴纸，实现对智能导航系统的隐蔽攻击。
Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
- 在物体上贴可学习纹理和透明度的对抗贴纸，实现物理世界攻击。
- 多视角优化使攻击在不同视角下仍有效，成功率下降22.39%。
- 贴纸自然隐蔽，适合研究智能系统安全漏洞的开发者参考。
具身视觉导航的显著进展引发了对其深度神经网络易受对抗攻击的担忧。尤其在存在3D物理攻击威胁时，此类风险可能危及人类安全。然而，现有具身导航攻击方法因难以将数字扰动转化为物理世界而缺乏可行性。此外，当前针对目标检测的物理攻击在导航场景中难以同时实现多视角有效性与视觉自然性。为此，我们提出一种实用的具身导航攻击方法：在物体上附加对抗贴纸，其透明度与纹理均可学习。为确保多视角有效性，采用基于物体感知采样的多视角优化策略，根据导航用视觉感知模型的反馈优化贴纸纹理。为使贴纸对人眼不显眼，引入两阶段透明度优化机制，即在纹理优化后微调透明度。实验表明，该对抗贴纸平均使导航成功率下降22.39%，在实用性、有效性和自然性上均优于先前方法。代码已开源：https://github.com/chen37058/Physical-Attacks-in-Embodied-Nav
原文摘要 · Abstract (English)
The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the adversarial robustness of embodied vision navigation is crucial, especially given the threat of 3D physical attacks that could pose risks to human safety. However, existing attack methods for embodied vision navigation often lack physical feasibility due to challenges in transferring digital perturbations into the physical world. Moreover, current physical attacks for object detection struggle to achieve both multi-view effectiveness and visual naturalness in navigation scenarios. To address this, we propose a practical attack method for embodied navigation by attaching adversarial patches to objects, where both opacity and textures are learnable. Specifically, to ensure effectiveness across varying viewpoints, we employ a multi-view optimization strategy based on object-aware sampling, which optimizes the patch's texture based on feedback from the vision-based perception model used in navigation. To make the patch inconspicuous to human observers, we introduce a two-stage opacity optimization mechanism, in which opacity is fine-tuned after texture optimization. Experimental results demonstrate that our adversarial patches decrease the navigation success rate by an average of 22.39%, outperforming previous methods in practicality, effectiveness, and naturalness. Code is available at: https://github.com/chen37058/Physical-Attacks-in-Embodied-Nav
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。