# Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks

arXiv: https://arxiv.org/abs/2504.01659 · HTML: https://mlsanity.com/paper/2504.01659/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation](https://mlsanity.com/paper/2107.05399/) (2021)
- [PointGuard: Provably Robust 3D Point Cloud Classification](https://mlsanity.com/paper/2103.03046/) (2021)
- [Minimal Adversarial Examples for Deep Learning on 3D Point Clouds](https://mlsanity.com/paper/2008.12066/) (2020)
- [Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification](https://mlsanity.com/paper/2111.10990/) (2021)
- [3D Adversarial Attacks Beyond Point Cloud](https://mlsanity.com/paper/2104.12146/) (2021)
- [Learning with Noisy Labels for Robust Point Cloud Segmentation](https://mlsanity.com/paper/2107.14230/) (2021)
- [Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters](https://mlsanity.com/paper/2107.09783/) (2021)
- [Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation](https://mlsanity.com/paper/2308.14619/) (2023)
- [Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients](https://mlsanity.com/paper/2203.15245/) (2022)
- [See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation](https://mlsanity.com/paper/2111.09450/) (2021)
- [UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps](https://mlsanity.com/paper/2403.17633/) (2024)
- [Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training](https://mlsanity.com/paper/2004.12724/) (2020)
- [LPF-Defense: 3D Adversarial Defense based on Frequency Analysis](https://mlsanity.com/paper/2202.11287/) (2022)
- [SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.05917/) (2022)
- [T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds](https://mlsanity.com/paper/2309.08302/) (2023)
- [Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training](https://mlsanity.com/paper/1711.08001/) (2017)
- [On Adversarial Robustness of Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2112.05871/) (2021)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) frameworks have shown good generalization capabilities for 3D point cloud semantic segmentation models on clean data. However, existing works overlook adversarial robustness when the source domain itself is compromised. To comprehensively explore the robustness of the UDA frameworks, we first design a stealthy adversarial point cloud generation attack that can significantly contaminate datasets with only minor perturbations to the point cloud surface. Based on that, we propose a novel dataset, AdvSynLiDAR, comprising synthesized contaminated LiDAR point clouds. With the generated corrupted data, we further develop the Adversarial Adaptation Framework (AAF) as the countermeasure. Specifically, by extending the key point sensitive (KPS) loss towards the Robust Long-Tail loss (RLT loss) and utilizing a decoder branch, our approach enables the model to focus on long-tail classes during the pre-training phase and leverages high-confidence decoded point cloud information to restore point cloud structures during the adaptation phase. We evaluated our AAF method on the AdvSynLiDAR dataset, where the results demonstrate that our AAF method can mitigate performance degradation under source adversarial perturbations for UDA in the 3D point cloud segmentation application.