Explainability-Aware One Point Attack for Point Cloud Neural Networks
This addresses the reliability and explainability of 3D object recognition models, offering a novel approach for understanding model vulnerabilities, though it is incremental in focusing on point cloud-specific attacks.
The paper tackles the problem of adversarial attacks on point cloud neural networks by proposing two methods (OPA and CTA) that use explainability to target critical points, achieving nearly 100% success rate in deceiving networks by shifting only one point.
With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of point cloud networks by adversarial attacks. However, most of the existing studies aim to deceive humans or defense algorithms, while the few that address the operation principles of the models themselves remain flawed in terms of critical point selection. In this work, we propose two adversarial methods: One Point Attack (OPA) and Critical Traversal Attack (CTA), which incorporate the explainability technologies and aim to explore the intrinsic operating principle of point cloud networks and their sensitivity against critical points perturbations. Our results show that popular point cloud networks can be deceived with almost $100\%$ success rate by shifting only one point from the input instance. In addition, we show the interesting impact of different point attribution distributions on the adversarial robustness of point cloud networks. Finally, we discuss how our approaches facilitate the explainability study for point cloud networks. To the best of our knowledge, this is the first point-cloud-based adversarial approach concerning explainability. Our code is available at https://github.com/Explain3D/Exp-One-Point-Atk-PC.