Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification

Liu, Daizong; Hu, Wei

doi:10.1109/tpami.2022.3193449

Cited by 24 publications

(27 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the imperceptibility of our NormalAttack, we compare the distance metrics with FGSM, I-FGSM [36], 3D-ADV [11], GeoA 3 [32], and ITA * [34]. e results reported in Table 1 show that all these methods can achieve 100% attack success rates.…”

Section: Quantitative Resultsmentioning

confidence: 99%

“…Differently, they enforce the perturbation to be attached to the manifold, while our NormalAttack attempts to destroy the manifold. We notice a concurrent work [34] that also moves points along normals. Differently, instead of strictly restrict the moving direction, we allow points to be slightly shifted along the tangent plane, such that more feasible solutions can be searched.…”

Section: Geometry-aware Adversarial Attacksmentioning

confidence: 94%

“…We compare the Normal-Attack framework with five baseline attack methods, e.g., FGSM, I-FGSM [36], 3D-ADV [11], GeoA 3 [32], and ITA * [34]. Note that ITA * indicates the method that implements the directional perturbation module of ITA with the adversarial transformation model for black-box attack ablated.…”

Section: Baseline Attack Methodsmentioning

confidence: 99%

“…To guide the perturbation to be concentrated along normals such that the underlying surfaces are deformed after applying it, we devise a deformation guiding module (DGM). Instead of strictly restrict normals as the only available moving directions as in ITA [34], DGM applies a much more soft constraint. Suppose 􏽢 P is the adversarial point cloud generated from P, 􏽢 p i denotes the corresponding point of p i in 􏽢 P, and p i 􏽢 p i ��→ denotes the vector from p i to 􏽢 p i , the projected perturbation in the tangent direction can be calculated as follows:…”

Section: Deformation Guiding Modulementioning

confidence: 99%

“…Discussion with ITA. Compared with ITA [34], our DGM allows larger freedom along the tangent plane, and thus more feasible solutions can be searched. Besides, adding these offsets in the tangent direction can be considered as applying an additional re-sampling process, thus making the surfaces after perturbation more smooth, as shown in Figure 3.…”

Section: Deformation Guiding Modulementioning

confidence: 99%

See 4 more Smart Citations

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

Tang

Shi

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Many efforts have been made on developing adversarial attack methods on point clouds. However, without fully considering the geometric property of point clouds, existing methods tend to produce clearly visible outliers. In this paper, we propose a novel NormalAttack framework towards imperceptible adversarial attacks on point clouds. First, we enforce the perturbation to be concentrated along normals to deform the underlying surface of 3D point clouds, such that tiny perturbation can make the shape deformed for better attack performance. Second, we guide the perturbation to be located more on regions with larger curvature, such that better imperceptibility is achieved. Extensive experiments on three representative networks, e.g., PointNet++, DGCNN, and PointConv, validate the effectiveness of NormalAttack and its superiority to state-of-the-art methods.

show abstract

Section: Quantitative Resultsmentioning

confidence: 99%

Section: Geometry-aware Adversarial Attacksmentioning

confidence: 94%

Section: Baseline Attack Methodsmentioning

confidence: 99%

Section: Deformation Guiding Modulementioning

confidence: 99%

Section: Deformation Guiding Modulementioning

confidence: 99%

See 3 more Smart Citations

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

Tang

Shi

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

Liu

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

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

Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification

Cited by 24 publications

References 56 publications

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

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

Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks

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

Contact Info

Product

Resources

About