mlsanityData to 14 Oct 2026

CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction

arXiv 2404.14042 ↗First posted 22 Apr 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

The increasing adoption of 3D point cloud data in various applications, such as autonomous vehicles, robotics, and virtual reality, has brought about significant advancements in object recognition and scene understanding. However, this progress is accompanied by new security challenges, particularly in the form of backdoor attacks. These attacks involve inserting malicious information into the training data of machine learning models, potentially compromising the model's behavior. In this paper, we propose CloudFort, a novel defense mechanism designed to enhance the robustness of 3D point cloud classifiers against backdoor attacks. CloudFort leverages spatial partitioning and ensemble prediction techniques to effectively mitigate the impact of backdoor triggers while preserving the model's performance on clean data. We evaluate the effectiveness of CloudFort through extensive experiments, demonstrating its strong resilience against the Point Cloud Backdoor Attack (PCBA). Our results show that CloudFort significantly enhances the security of 3D point cloud classification models without compromising their accuracy on benign samples. Furthermore, we explore the limitations of CloudFort and discuss potential avenues for future research in the field of 3D point cloud security. The proposed defense mechanism represents a significant step towards ensuring the trustworthiness and reliability of point-cloud-based systems in real-world applications.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

28 of 50 references.

References · 28

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  7. 2022Diffusion Models for Adversarial Purificationcited by 476
  8. 2020Backdoor Learning: A Surveycited by 426
  9. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  10. 2019Label-Consistent Backdoor Attackscited by 296
  11. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 235
  12. 2019Detecting AI Trojans Using Meta Neural Analysiscited by 199
16 more
  1. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 161
  2. 2020RAB: Provable Robustness Against Backdoor Attackscited by 118
  3. 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 108
  4. 2020Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoffcited by 89
  5. 2020DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentationcited by 77
  6. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 73
  7. 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
  8. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  9. 2021A Backdoor Attack against 3D Point Cloud Classifierscited by 53
  10. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  11. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 35
  12. 2021Direct LiDAR Odometry: Fast Localization with Dense Point Cloudscited by 30
  13. 2022Imperceptible and Robust Backdoor Attack in 3D Point Cloudcited by 25
  14. 2020Depth-Adapted CNN for RGB-D camerascited by 12
  15. 2021Detecting Backdoor Attacks Against Point Cloud Classifierscited by 10
  16. 2023Risk-optimized Outlier Removal for Robust 3D Point Cloud Classificationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
  2. 2024Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features
  3. 2025Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness
  4. 2022PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition
  5. 2025STONE: Pioneering the One-to-N Universal Backdoor Threat in 3D Point Cloud
  6. 2025Multimodal Robust Prompt Distillation for 3D Point Cloud Models
  7. 2024PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
  8. 2024BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection