# IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

arXiv: https://arxiv.org/abs/2010.05272 · HTML: https://mlsanity.com/paper/2010.05272/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2020.

## Built on by (most cited first, 30 of 46)

- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [PointGuard: Provably Robust 3D Point Cloud Classification](https://mlsanity.com/paper/2103.03046/) (2021)
- [Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification](https://mlsanity.com/paper/2111.10990/) (2021)
- [DISCO: Adversarial Defense with Local Implicit Functions](https://mlsanity.com/paper/2212.05630/) (2022)
- [3D Adversarial Attacks Beyond Point Cloud](https://mlsanity.com/paper/2104.12146/) (2021)
- [Isometric 3D Adversarial Examples in the Physical World](https://mlsanity.com/paper/2210.15291/) (2022)
- [Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds](https://mlsanity.com/paper/2403.05247/) (2024)
- [Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks](https://mlsanity.com/paper/2202.07261/) (2022)
- [Boosting 3D Adversarial Attacks with Attacking On Frequency](https://mlsanity.com/paper/2201.10937/) (2022)
- [Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients](https://mlsanity.com/paper/2203.15245/) (2022)
- [Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing](https://mlsanity.com/paper/2207.13326/) (2022)
- [PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition](https://mlsanity.com/paper/2208.09801/) (2022)
- [LPF-Defense: 3D Adversarial Defense based on Frequency Analysis](https://mlsanity.com/paper/2202.11287/) (2022)
- [Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion](https://mlsanity.com/paper/2211.16247/) (2022)
- [Local Aggressive Adversarial Attacks on 3D Point Cloud](https://mlsanity.com/paper/2105.09090/) (2021)
- [Toward Availability Attacks in 3D Point Clouds](https://mlsanity.com/paper/2407.11011/) (2024)
- [The art of defense: letting networks fool the attacker](https://mlsanity.com/paper/2104.02963/) (2021)
- [PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees](https://mlsanity.com/paper/2303.01959/) (2023)
- [Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification](https://mlsanity.com/paper/2307.10875/) (2023)
- [Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions](https://mlsanity.com/paper/2309.10431/) (2023)
- [Improving transferability of 3D adversarial attacks with scale and shear transformations](https://mlsanity.com/paper/2211.01093/) (2022)
- [Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey](https://mlsanity.com/paper/2307.00309/) (2023)
- [Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples](https://mlsanity.com/paper/2307.16361/) (2023)
- [Towards Robust 3D Pose Transfer with Adversarial Learning](https://mlsanity.com/paper/2404.02242/) (2024)
- [On Adversarial Robustness of Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2112.05871/) (2021)
- [Random Walks for Adversarial Meshes](https://mlsanity.com/paper/2202.07453/) (2022)
- [Robustifying Point Cloud Networks by Refocusing](https://mlsanity.com/paper/2308.05525/) (2023)
- [PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification](https://mlsanity.com/paper/2403.06698/) (2024)
- [Robust 3D Point Clouds Classification based on Declarative Defenders](https://mlsanity.com/paper/2410.09691/) (2024)

## Abstract (arXiv)

Point cloud is an important 3D data representation widely used in many essential applications. Leveraging deep neural networks, recent works have shown great success in processing 3D point clouds. However, those deep neural networks are vulnerable to various 3D adversarial attacks, which can be summarized as two primary types: point perturbation that affects local point distribution, and surface distortion that causes dramatic changes in geometry. In this paper, we simultaneously address both the aforementioned attacks by learning to restore the clean point clouds from the attacked ones. More specifically, we propose an IF-Defense framework to directly optimize the coordinates of input points with geometry-aware and distribution-aware constraints. The former aims to recover the surface of point cloud through implicit function, while the latter encourages evenly-distributed points. Our experimental results show that IF-Defense achieves the state-of-the-art defense performance against existing 3D adversarial attacks on PointNet, PointNet++, DGCNN, PointConv and RS-CNN. For example, compared with previous methods, IF-Defense presents 20.02% improvement in classification accuracy against salient point dropping attack and 16.29% against LG-GAN attack on PointNet. Our code is available at https://github.com/Wuziyi616/IF-Defense.