Less Adaptation, More Transfer: Spectral View Randomization for 3D Point Cloud Transfer Attacks
Applied Sciences · 24.07.2026 · 16 (15) · 7421
DOI: 10.3390/app16157421 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 24.07.2026. Verfasst von Yang Gao und 4 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Point cloud perception is important in autonomous driving, robotics, and other security-critical 3D systems, yet learned point cloud classifiers remain vulnerable to transferable adversarial perturbations. A central difficulty in transfer-based black-box attacks is surrogate overfitting: an update that is highly effective on an accessible source model may not generalize to an unknown target architecture. We introduce SpecEOT, a source-agnostic and graph-spectral expectation-over-transformation attack. A fixed graph Fourier transform (GFT) basis is constructed from each clean point cloud. At every optimization iteration, each non-identity view independently samples a frequency band and a perturbation sign from uniform distributions; the resulting view gradients are averaged with equal weights and used to update the adversarial point cloud through projected Adam ascent. We evaluate the stochastic method over repeated seeds, extend the ablation to two source architectures, and analyze the interaction between band count and randomization strength while reporting computational cost and assessing robustness to Gaussian jitter and point dropout. SpecEOT achieves strong transferability on ModelNet40 and ShapeNet.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Gao, Y., Liu, J., Liu, H., Li, H., & Xu, J. (2026). Less Adaptation, More Transfer: Spectral View Randomization for 3D Point Cloud Transfer Attacks. Applied Sciences, 16(15), 7421. https://doi.org/10.3390/app16157421
Vancouver
Gao Y, Liu J, Liu H, Li H, Xu J. Less Adaptation, More Transfer: Spectral View Randomization for 3D Point Cloud Transfer Attacks. Applied Sciences. 2026;16(15):7421. doi:10.3390/app16157421
BibTeX
@article{Gao2026,
author = {Gao, Yang and Liu, Jingyi and Liu, Hongjia and Li, Haoran and Xu, Jian},
title = {Less Adaptation, More Transfer: Spectral View Randomization for 3D Point Cloud Transfer Attacks},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {15},
pages = {7421},
doi = {10.3390/app16157421}
}
EUVIMED