Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation

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: github.com/chen37058/Physical-Attacks-in-Embodied-Nav.

Authors

• Meng Chen
• Jiawei Tu
• Chao Qi
• Yonghao Dang
• Feng Zhou
• Wei Wei
• Jianqin Yin

Keywords

• Visualization
• Navigation
• Perturbation methods
• Object detection
• Observers
• Three-dimensional printing
• Rendering (computer graphics)
• Robustness
• Safety
• Optimization
• Adversarial Attacks
• Deep Neural Network
• Physical World
• Physical Attacks
• Attack Methods
• Adversarial Robustness
• Point Cloud
• Detection Model
• Bounding Box
• Face Recognition
• Target Object
• Depth Camera
• Objects In The Scene
• Navigation Task
• Mask R-CNN
• Adversarial Examples
• Detection Confidence
• Projected Gradient Descent
• Attack Success Rate
• 3D Texture
• Attack Performance
• Viewpoint Variations
• Unseen Environments