Rethinking Perturbation Directions for Imperceptible Adversarial Attacks on Point Clouds

Tang, Keke; Shi, Yawen; Lou, Tianrui; Peng, Weilong; He, Xu; Zhu, Peican; Gu, Zhaoquan; Tian, Zhihong

doi:10.1109/jiot.2022.3222159

Cited by 20 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is intuitive to ask the question: Whether it is also effective to attack the features of middle layers? Various scholars devote their efforts to tackling this question [39,40]. Zhou et al presented the Transferable Adversarial Perturbations (TAP) to improve the transferability through increasing the feature distances between the original image and its adversarial example in the intermediate layers [41].…”

Section: Related Workmentioning

confidence: 99%

SGMA: a novel adversarial attack approach with improved transferability

Zhu

Hong²,

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

Deep learning models are easily deceived by adversarial examples, and transferable attacks are crucial because of the inaccessibility of model information. Existing SOTA attack approaches tend to destroy important features of objects to generate adversarial examples. This paper proposes the split grid mask attack (SGMA), which reduces the intensity of model-specific features by split grid mask transformation, effectively highlighting the important features of the input image. Perturbing these important features can guide the development of adversarial examples in a more transferable direction. Specifically, we introduce the split grid mask transformation into the input image. Due to the vulnerability of model-specific features to image transformations, the intensity of model-specific features decreases after aggregation while the intensities of important features remain. The generated adversarial examples guided by destroying important features have excellent transferability. Extensive experimental results demonstrate the effectiveness of the proposed SGMA. Compared to the SOTA attack approaches, our method improves the black-box attack success rates by an average of 6.4% and 8.2% against the normally trained models and the defense ones respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

SGMA: a novel adversarial attack approach with improved transferability

Zhu

Hong²,

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Generative approaches utilize models such as Generative Adversarial Networks (GANs) and variational autoencoder models to create adversarial point clouds. Most of these attacks [56,57,88,89] attempt to change the shape of the point cloud in order to fool the deep model. The concept of these attacks can be related to what is called unrestricted attacks in 2D images [90,91,92].…”

Section: ) Generative Strategiesmentioning

confidence: 99%

“…Tang et al [88] proposed a deep manifold attack that deforms the intrinsic 2-manifold structures of 3D point clouds. The attack strategy comprises two steps.…”

Section: ) Generative Strategiesmentioning

confidence: 99%

“…Datasets ModelNet10 [119] [67], [107], [130], [82] ModelNet40 [119] [60], [67], [65], [63], [62], [61], [59], [57], [58], [54] [53], [98], [78], [131], [101], [132], [107], [133], [130], [73] [56], [96], [82], [79], [64], [100], [134], [106], [135], [76], [85], [136] ShapeNet [120] [61], [57], [55], [98], [131], [79], [93], [105] ScanObjectNN [121] [63], [132], [113], [107], [130] KITTI [126] [67], [137] ScanNet [19] [113], [106] 3D-MNIST…”

Section: ) Understanding the Role Of Frequencymentioning

confidence: 99%

“…PointNet [19] [60], [67], [66], [65], [63], [62], [61], [57], [58], [55] [54], [53], [98], [101], [74], [132], [113], [107], [133], [130] [89], [73], [56], [96], [82], [79], [93], [105], [64], [100] [137], [134], [106], [135], [76], [85], [136] PointNet++ [138] [60], [66], [65], [63], [62], [61], [59], [57], [58], [55] [54], [53], [98], [78], [131], [101], …”

Section: ) Understanding the Role Of Frequencymentioning

confidence: 99%

See 2 more Smart Citations

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

Enhancing Adversarial Robustness via Anomaly-aware Adversarial Training

Tang

Lou

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Rethinking Perturbation Directions for Imperceptible Adversarial Attacks on Point Clouds

Cited by 20 publications

References 34 publications

SGMA: a novel adversarial attack approach with improved transferability

SGMA: a novel adversarial attack approach with improved transferability

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

Enhancing Adversarial Robustness via Anomaly-aware Adversarial Training

Contact Info

Product

Resources

About