Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models

Understand

We propose a universal and physically realizable adversarial attack on a cascaded multi-modal deep learning network (DNN), in the context of self-driving cars.

• DNNs have achieved high performance in 3D object detection, but they are known to be vulnerable to adversarial attacks.
• These attacks have been heavily investigated in the RGB image domain and more recently in the point cloud domain, but rarely in both domains simultaneously - a gap to be filled in this paper.
• We use a single 3D mesh and differentiable rendering to explore how perturbing the mesh's geometry and texture can reduce the robustness of DNNs to adversarial attacks.