Adversarial Attack by Limited Point Cloud Surface Modifications
- URL: http://arxiv.org/abs/2110.03745v1
- Date: Thu, 7 Oct 2021 18:58:18 GMT
- Title: Adversarial Attack by Limited Point Cloud Surface Modifications
- Authors: Atrin Arya, Hanieh Naderi and Shohreh Kasaei
- Abstract summary: adversarial attack methods do not restrict the point modifications enough to preserve the point cloud appearance.
The proposed method addresses this issue by using a high step-size at the beginning of the algorithm to search the main surface of the point cloud.
The obtained results show that it can perform successful attacks and achieve state-of-the-art results by only a limited number of point modifications.
- Score: 11.325135016306165
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent research has revealed that the security of deep neural networks that
directly process 3D point clouds to classify objects can be threatened by
adversarial samples. Although existing adversarial attack methods achieve high
success rates, they do not restrict the point modifications enough to preserve
the point cloud appearance. To overcome this shortcoming, two constraints are
proposed. These include applying hard boundary constraints on the number of
modified points and on the point perturbation norms. Due to the restrictive
nature of the problem, the search space contains many local maxima. The
proposed method addresses this issue by using a high step-size at the beginning
of the algorithm to search the main surface of the point cloud fast and
effectively. Then, in order to converge to the desired output, the step-size is
gradually decreased. To evaluate the performance of the proposed method, it is
run on the ModelNet40 and ScanObjectNN datasets by employing the
state-of-the-art point cloud classification models; including PointNet,
PointNet++, and DGCNN. The obtained results show that it can perform successful
attacks and achieve state-of-the-art results by only a limited number of point
modifications while preserving the appearance of the point cloud. Moreover, due
to the effective search algorithm, it can perform successful attacks in just a
few steps. Additionally, the proposed step-size scheduling algorithm shows an
improvement of up to $14.5\%$ when adopted by other methods as well. The
proposed method also performs effectively against popular defense methods.
Related papers
- Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm [6.515472477685614]
The susceptibility of deep neural networks (DNNs) to adversarial attacks undermines their reliability across numerous applications.
We introduce the Enhanced Targeted DeepFool (ET DeepFool) algorithm, an evolution of DeepFool.
Our empirical investigations demonstrate the superiority of this refined approach in maintaining the integrity of images.
arXiv Detail & Related papers (2023-10-18T18:50:39Z) - Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification [54.286437930350445]
This paper highlights the challenges of point cloud classification posed by various forms of noise.
We introduce an innovative point outlier cleansing method that harnesses the power of downstream classification models.
Our proposed technique not only robustly filters diverse point cloud outliers but also consistently and significantly enhances existing robust methods for point cloud classification.
arXiv Detail & Related papers (2023-07-20T13:47:30Z) - FreePoint: Unsupervised Point Cloud Instance Segmentation [72.64540130803687]
We propose FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds.
We represent point features by combining coordinates, colors, and self-supervised deep features.
Based on the point features, we segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
arXiv Detail & Related papers (2023-05-11T16:56:26Z) - PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models
Against Adversarial Examples [63.84378007819262]
We propose PointCA, the first adversarial attack against 3D point cloud completion models.
PointCA can generate adversarial point clouds that maintain high similarity with the original ones.
We show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01.
arXiv Detail & Related papers (2022-11-22T14:15:41Z) - PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
Point cloud completion refers to completing 3D shapes from partial 3D point clouds.
We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs.
The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
arXiv Detail & Related papers (2022-03-16T09:20:01Z) - Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm [93.80082636284922]
Sparse adversarial attacks can fool deep networks (DNNs) by only perturbing a few pixels.
Recent efforts combine it with another l_infty perturbation on magnitudes.
We propose a homotopy algorithm to tackle the sparsity and neural perturbation framework.
arXiv Detail & Related papers (2021-06-10T20:11:36Z) - PointCutMix: Regularization Strategy for Point Cloud Classification [7.6904253666422395]
We propose a simple and effective augmentation method for the point cloud data, named PointCutMix.
It finds the optimal assignment between two point clouds and generates new training data by replacing the points in one sample with their optimal assigned pairs.
arXiv Detail & Related papers (2021-01-05T11:39:06Z) - Deep Magnification-Flexible Upsampling over 3D Point Clouds [103.09504572409449]
We propose a novel end-to-end learning-based framework to generate dense point clouds.
We first formulate the problem explicitly, which boils down to determining the weights and high-order approximation errors.
Then, we design a lightweight neural network to adaptively learn unified and sorted weights as well as the high-order refinements.
arXiv Detail & Related papers (2020-11-25T14:00:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.