mlsanityData to 14 Oct 2026

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

arXiv 2207.07539 ↗First posted 15 Jul 2022cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 15 Jul 2022.

Builds on

34 of 46 references.

References · 34

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  8. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  10. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  11. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  12. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
22 more
  1. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  2. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  3. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
  4. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
  5. 2018Generating 3D Adversarial Point Cloudscited by 144
  6. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  7. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 125
  8. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  9. 2016Shape Completion Enabled Robotic Graspingcited by 79
  10. 2020Robustness Verification for Transformerscited by 76
  11. 2019Adversarial Attack and Defense on Point Setscited by 63
  12. 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 63
  13. 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
  14. 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
  15. 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
  16. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  17. 2020How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networkscited by 32
  18. 2020ShapeAdv: Generating Shape-Aware Adversarial 3D Point Cloudscited by 20
  19. 2021Robustness Certification for Point Cloud Modelscited by 16
  20. 2020Defense-PointNet: Protecting PointNet Against Adversarial Attackscited by 13
  21. 2021Sparse Adversarial Video Attacks with Spatial Transformationscited by 11
  22. 2018Visualization and Labeling of Point Clouds in Virtual Realitycited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4.

5 papers.

  1. 2023Towards Verifying the Geometric Robustness of Large-scale Neural Networkscited by 11
  2. 2023Reachability Analysis of Neural Network Control Systemscited by 8
  3. 2022Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learningcited by 7
  4. 2023Reward Certification for Policy Smoothed Reinforcement Learningcited by 7
  5. 2023Model-Agnostic Reachability Analysis on Deep Neural Networkscited by 1