# Desensitizing for Improving Corruption Robustness in Point Cloud Classification through Adversarial Training

arXiv: https://arxiv.org/abs/2509.23010 · HTML: https://mlsanity.com/paper/2509.23010/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 29 of 29)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Self-Knowledge Distillation with Progressive Refinement of Targets](https://mlsanity.com/paper/2006.12000/) (2020)
- [PointMixup: Augmentation for Point Clouds](https://mlsanity.com/paper/2008.06374/) (2020)
- [Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers](https://mlsanity.com/paper/1901.03006/) (2019)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://mlsanity.com/paper/2201.12296/) (2022)
- [Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud](https://mlsanity.com/paper/2012.10921/) (2020)
- [Benchmarking and Analyzing Point Cloud Classification under Corruptions](https://mlsanity.com/paper/2202.03377/) (2022)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Shapley Explanation Networks](https://mlsanity.com/paper/2104.02297/) (2021)
- [Meta Architecture for Point Cloud Analysis](https://mlsanity.com/paper/2211.14462/) (2022)
- [Attention-based Point Cloud Edge Sampling](https://mlsanity.com/paper/2302.14673/) (2023)
- [Self-Distillation from the Last Mini-Batch for Consistency Regularization](https://mlsanity.com/paper/2203.16172/) (2022)
- [Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds](https://mlsanity.com/paper/2403.05247/) (2024)
- [Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value](https://mlsanity.com/paper/2208.03608/) (2022)
- [Fast Hierarchical Games for Image Explanations](https://mlsanity.com/paper/2104.06164/) (2021)
- [Joint Representation Learning for Text and 3D Point Cloud](https://mlsanity.com/paper/2301.07584/) (2023)
- [Interpreting Representation Quality of DNNs for 3D Point Cloud Processing](https://mlsanity.com/paper/2111.03549/) (2021)

## Abstract (arXiv)

Due to scene complexity, sensor inaccuracies, and processing imprecision, point cloud corruption is inevitable. Over-reliance on input features is the root cause of DNN vulnerabilities. It remains unclear whether this issue exists in 3D tasks involving point clouds and whether reducing dependence on these features can enhance the model's robustness to corrupted point clouds. This study attempts to answer these questions. Specifically, we quantified the sensitivity of the DNN to point cloud features using Shapley values and found that models trained using traditional methods exhibited high sensitivity values for certain features. Furthermore, under an equal pruning ratio, prioritizing the pruning of highly sensitive features causes more severe damage to model performance than random pruning. We propose `Desensitized Adversarial Training' (DesenAT), generating adversarial samples using feature desensitization and conducting training within a self-distillation framework, which aims to alleviate DNN's over-reliance on point clouds features by smoothing sensitivity. First, data points with high contribution components are eliminated, and spatial transformation is used to simulate corruption scenes, generate adversarial samples, and conduct adversarial training on the model. Next, to compensate for information loss in adversarial samples, we use the self-distillation method to transfer knowledge from clean samples to adversarial samples, and perform adversarial training in a distillation manner.Extensive experiments on ModelNet-C and PointCloud-C demonstrate show that the propose method can effectively improve the robustness of the model without reducing the performance of clean data sets. This code is publicly available at hrefhttps://github.com/JerkyT/DesenAT/tree/masterhttps://github.com/JerkyT/DesenAT.