NormalAttack: Curvature-Aware Shape Deformation along Normals for Imperceptible Point Cloud Attack

Tang, Keke; Shi, Yawen; Wu, Jianpeng; Peng, Weilong; Khan, Asad; Zhu, Peican; Gu, Zhaoquan

doi:10.1155/2022/1186633

Cited by 9 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although some of the attacks described earlier also involve shifting points, the main difference here is that ITA aims to make the attack imperceptible, whereas earlier attacks may cause noticeable changes to the shape. Along the same lines, Tang et al [81] presented a method called NormalAttack for generating imperceptible point cloud attacks. Their method deforms objects along their normals by considering the object's curvature to make the modification less noticeable.…”

Section: ) Point Shift Attacksmentioning

confidence: 99%

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Naderi,

Bajić

2023

IEEE Access

View full text Add to dashboard Cite

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds has become increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye, but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point-cloud classification. This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain. INDEX TERMS 3D deep learning, deep neural network, adversarial examples, adversarial defense, machine learning security, 3D point clouds.

show abstract

Section: ) Point Shift Attacksmentioning

confidence: 99%

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Naderi,

Bajić

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Deep 3D Point Cloud Classification. Deep learning techniques for 3D point cloud classification have evolved significantly (Bronstein et al 2017;Tang et al 2022a;Tang, Song, and Chen 2016;Chen et al 2022), moving from initial voxel grid methods (Maturana and Scherer 2015) to advanced direct processing of points (Qi et al 2017;Wu, Qi, and Fuxin 2019). We aim to attack these classifiers imperceptibly.…”

Section: Related Workmentioning

confidence: 99%

“…Typical methodologies to ensure the imperceptibility of adversarial attacks on 3D point clouds employ metrics such as the l 2 -norm, Chamfer distance, and Hausdorff distance to constrain the perturbation. More recent studies have sought to further reduce the distortion by limiting the change of curvature (Wen et al 2022), guiding the perturbation along the normal direction (Liu and Hu 2023;Tang et al 2022c) and along the tangential direction (Huang et al 2022), etc. Despite these advances, the generated adversarial point clouds do not yet achieve the desired level of imperceptibility, often exhibiting noticeable outliers or deformations in shape.…”

Section: Introductionmentioning

confidence: 99%

Manifold Constraints for Imperceptible Adversarial Attacks on Point Clouds

Tang,

He,

Peng

et al. 2024

AAAI

View full text Add to dashboard Cite

Adversarial attacks on 3D point clouds often exhibit unsatisfactory imperceptibility, which primarily stems from the disregard for manifold-aware distortion, i.e., distortion of the underlying 2-manifold surfaces. In this paper, we develop novel manifold constraints to reduce such distortion, aiming to enhance the imperceptibility of adversarial attacks on 3D point clouds. Specifically, we construct a bijective manifold mapping between point clouds and a simple parameter shape using an invertible auto-encoder. Consequently, manifold-aware distortion during attacks can be captured within the parameter space. By enforcing manifold constraints that preserve local properties of the parameter shape, manifold-aware distortion is effectively mitigated, ultimately leading to enhanced imperceptibility. Extensive experiments demonstrate that integrating manifold constraints into conventional adversarial attack solutions yields superior imperceptibility, outperforming the state-of-the-art methods.

show abstract

“…Data points that have closer spatial curvatures are more likely to possess similar attribute values. Therefore, when applying Gaussian mixture models for spatial clustering, it is advisable to incorporate relevant spatial curvature constraints to optimize the clustering algorithm [22][23][24].…”

Section: Curvature-based Spatial Neighborhood Information Functionmentioning

confidence: 99%

Clustering and Segmentation of Adhesive Pests in Apple Orchards Based on GMM-DC

Wang,

Liu,

Ren

et al. 2023

Agronomy

View full text Add to dashboard Cite

The segmentation of individual pests is a prerequisite for pest feature extraction and identification. To address the issue of pest adhesion in the apple orchard pest identification process, this research proposed a pest adhesion image segmentation method based on Gaussian Mixture Model with Density and Curvature Weighting (GMM-DC). First, in the HSV color space, an image was desaturated by adjusting the hue and inverting to mitigate threshold crossing points. Subsequently, threshold segmentation and contour selection methods were used to separate the image background. Next, a shape factor was introduced to determine the regions and quantities of adhering pests, thereby determining the number of model clustering clusters. Then, point cloud reconstruction was performed based on the color and spatial distribution features of the pests. To construct the GMM-DC segmentation model, a spatial density (SD) and spatial curvature (SC) information function were designed and embedded in the GMM. Finally, experimental analysis was conducted on the collected apple orchard pest images. The results showed that GMM-DC achieved an average accurate segmentation rate of 95.75%, an average over-segmentation rate of 2.83%, and an average under-segmentation rate of 1.42%. These results significantly outperformed traditional image segmentation methods. In addition, the original and improved Mask R-CNN models were used as recognition models, and the mean Average Precision was used as the evaluation metric. Recognition experiments were conducted on pest images with and without the proposed method. The results show the mean Average Precision for pest images segmented with the proposed method as 92.43% and 96.75%. This indicates an improvement of 13.01% and 12.18% in average recognition accuracy, respectively. The experimental results demonstrate that this method provides a theoretical and methodological foundation for accurate pest identification in orchards.

show abstract

NormalAttack: Curvature-Aware Shape Deformation along Normals for Imperceptible Point Cloud Attack

Cited by 9 publications

References 32 publications

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Manifold Constraints for Imperceptible Adversarial Attacks on Point Clouds

Clustering and Segmentation of Adhesive Pests in Apple Orchards Based on GMM-DC

Contact Info

Product

Resources

About