Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds
Not on the map. Why?
Abstract (arXiv)
Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surgery to earth observation from low orbit. As with other ML tasks, classification models are notoriously brittle in the presence of adversarial attacks. These are rooted in imperceptible changes to inputs with the effect that a seemingly well-trained model ends up misclassifying the input. This paper adds to the understanding of adversarial attacks by presenting Eidos, a framework providing Efficient Imperceptible aDversarial attacks on 3D pOint cloudS. Eidos supports a diverse set of imperceptibility metrics. It employs an iterative, two-step procedure to identify optimal adversarial examples, thereby enabling a runtime-imperceptibility trade-off. We provide empirical evidence relative to several popular 3D point cloud classification models and several established 3D attack methods, showing Eidos' superiority with respect to efficiency as well as imperceptibility.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 23 May 2024.
Builds on
25 of 42 references.
References · 25
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2016Adversarial examples in the physical worldcited by 1,769
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2019Simple Black-box Adversarial Attackscited by 251
- 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
- 2018Generating 3D Adversarial Point Cloudscited by 144
- 2018PointCloud Saliency Mapscited by 112
13 more
- 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
- 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
- 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
- 2019Adversarial Attack and Defense on Point Setscited by 63
- 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
- 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
- 2022Shape-invariant 3D Adversarial Point Cloudscited by 50
- 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
- 2020Learning Black-Box Attackers with Transferable Priors and Query Feedbackcited by 32
- 20213D Adversarial Attacks Beyond Point Cloudcited by 26
- 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
- 2022Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attackscited by 19
- 2019Walking on the Edge: Fast, Low-Distortion Adversarial Examplescited by 18
Built on by
Citing papers per year: 2025: 1.
1 paper.