Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets
Graph Signal Processing
- URL: http://arxiv.org/abs/2207.13326v2
- Date: Thu, 7 Dec 2023 07:05:12 GMT
- Title: Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets
Graph Signal Processing
- Authors: Daizong Liu, Wei Hu, Xin Li
- Abstract summary: Point cloud learning models have been shown to be vulnerable to adversarial attacks.
We propose the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that corresponds to varying geometric structure.
Experimental results demonstrate the effectiveness of the proposed attack in terms of both the imperceptibility and attack success rates.
- Score: 30.86044518259855
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With the increasing attention in various 3D safety-critical applications,
point cloud learning models have been shown to be vulnerable to adversarial
attacks. Although existing 3D attack methods achieve high success rates, they
delve into the data space with point-wise perturbation, which may neglect the
geometric characteristics. Instead, we propose point cloud attacks from a new
perspective -- the graph spectral domain attack, aiming to perturb graph
transform coefficients in the spectral domain that corresponds to varying
certain geometric structure. Specifically, leveraging on graph signal
processing, we first adaptively transform the coordinates of points onto the
spectral domain via graph Fourier transform (GFT) for compact representation.
Then, we analyze the influence of different spectral bands on the geometric
structure, based on which we propose to perturb the GFT coefficients via a
learnable graph spectral filter. Considering the low-frequency components
mainly contribute to the rough shape of the 3D object, we further introduce a
low-frequency constraint to limit perturbations within imperceptible
high-frequency components. Finally, the adversarial point cloud is generated by
transforming the perturbed spectral representation back to the data domain via
the inverse GFT. Experimental results demonstrate the effectiveness of the
proposed attack in terms of both the imperceptibility and attack success rates.
Related papers
- ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization.
This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
arXiv Detail & Related papers (2024-03-15T14:35:05Z) - Compressive Recovery of Signals Defined on Perturbed Graphs [4.021249101488848]
We present an algorithm which simultaneously recovers the signal from the compressive measurements and also corrects the graph perturbations.
An application to compressive image reconstruction is also presented, where graph perturbations are modeled as undesirable graph edges linking pixels with significant intensity difference.
arXiv Detail & Related papers (2024-02-12T13:20:52Z) - HoloNets: Spectral Convolutions do extend to Directed Graphs [59.851175771106625]
Conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs.
Here we show this traditional reliance on the graph Fourier transform to be superfluous.
We provide a frequency-response interpretation of newly developed filters, investigate the influence of the basis used to express filters and discuss the interplay with characteristic operators on which networks are based.
arXiv Detail & Related papers (2023-10-03T17:42:09Z) - PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis [82.91576069955619]
We introduce a new method, PointWavelet, to explore local graphs in the spectral domain via a learnable graph wavelet transform.
Specifically, we first introduce the graph wavelet transform to form multi-scale spectral graph convolution to learn effective local structural representations.
To avoid the time-consuming spectral decomposition, we then devise a learnable graph wavelet transform, which significantly accelerates the overall training process.
arXiv Detail & Related papers (2023-02-10T12:07:26Z) - Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction [120.08257447708503]
Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction.
We propose a novel skeleton-parted graph scattering network (SPGSN)
SPGSN outperforms state-of-the-art methods by remarkable margins of 13.8%, 9.3% and 2.7% in terms of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.
arXiv Detail & Related papers (2022-07-31T05:51:39Z) - Graph Structural Attack by Spectral Distance [35.998704625736394]
Graph Convolutional Networks (GCNs) have fueled a surge of interest due to their superior performance on graph learning tasks.
In this paper, an effective graph structural attack is investigated to disrupt graph spectral filters in the Fourier domain.
arXiv Detail & Related papers (2021-11-01T04:02:34Z) - A Hierarchical Graph Signal Processing Approach to Inference from
Spatiotemporal Signals [14.416786768268233]
Motivated by the emerging area of graph signal processing (GSP), we introduce a novel method to draw inference from signals.
In this paper we leverage techniques to develop a hierarchical feature extraction approach.
We test our approach on the intracranial EEG (iEEG) data set of the K aggle seizure detection contest.
arXiv Detail & Related papers (2020-10-25T17:08:13Z) - Offline detection of change-points in the mean for stationary graph
signals [55.98760097296213]
We propose an offline method that relies on the concept of graph signal stationarity.
Our detector comes with a proof of a non-asymptotic inequality oracle.
arXiv Detail & Related papers (2020-06-18T15:51:38Z) - Hypergraph Spectral Analysis and Processing in 3D Point Cloud [80.25162983501308]
3D point clouds have become a fundamental data structure to characterize 3D objects and surroundings.
To process 3D point clouds efficiently, a suitable model for the underlying structure and outlier noises is always critical.
We propose a hypergraph-based new point cloud model that is amenable to efficient analysis and processing.
arXiv Detail & Related papers (2020-01-08T05:30:16Z)
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.