3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models

TL;DR

3DVerifier is a novel, efficient framework for verifying the robustness of 3D point cloud models, capable of handling complex architectures like PointNet with improved speed and accuracy.

Contribution

The paper introduces 3DVerifier, a general verification framework that efficiently handles large-scale point cloud models with multiplication layers, outperforming existing methods.

Findings

Orders-of-magnitude faster verification for large networks

Tighter certified bounds compared to state-of-the-art

Effective handling of multiplication layers in PointNet

Abstract

3D point cloud models are widely applied in safety-critical scenes, which delivers an urgent need to obtain more solid proofs to verify the robustness of models. Existing verification method for point cloud model is time-expensive and computationally unattainable on large networks. Additionally, they cannot handle the complete PointNet model with joint alignment network (JANet) that contains multiplication layers, which effectively boosts the performance of 3D models. This motivates us to design a more efficient and general framework to verify various architectures of point cloud models. The key challenges in verifying the large-scale complete PointNet models are addressed as dealing with the cross-non-linearity operations in the multiplication layers and the high computational complexity of high-dimensional point cloud inputs and added layers. Thus, we propose an efficient verification framework, 3DVerifier, to tackle both challenges by adopting a linear relaxation function to bound the multiplication layer and combining forward and backward propagation to compute the certified bounds of the outputs of the point cloud models. Our comprehensive experiments demonstrate that 3DVerifier outperforms existing verification algorithms for 3D models in terms of both efficiency and accuracy. Notably, our approach achieves an orders-of-magnitude improvement in verification efficiency for the large network, and the obtained certified bounds are also significantly tighter than the state-of-the-art verifiers. We release our tool 3DVerifier via https://github.com/TrustAI/3DVerifier for use by the community.