TPAM: Transferable Perceptual-constrained Adversarial Meshes

Simple item page
dc.contributor.authorKang, Tengjiaen_US
dc.contributor.authorLi, Yuezunen_US
dc.contributor.authorZhou, Jiaranen_US
dc.contributor.authorXin, Shiqingen_US
dc.contributor.authorDong, Junyuen_US
dc.contributor.authorTu, Changheen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:03:45Z
dc.date.available2024-10-13T18:03:45Z
dc.date.issued2024
dc.description.abstractTriangle meshes are widely used in 3D data representation due to their efficacy in capturing complex surfaces. Mesh classification, crucial in various applications, has typically been tackled by Deep Neural Networks (DNNs) with advancements in deep learning. However, these mesh networks have been proven vulnerable to adversarial attacks, where slight distortions to meshes can cause large prediction errors, posing significant security risks. Although several mesh attack methods have been proposed recently, two key aspects of Stealthiness and Transferability remain underexplored. This paper introduces a new method called Transferable Perceptual-constrained Adversarial Meshes (TPAM) to investigate these aspects in adversarial attacks further. Specifically, we present a Perceptual-constrained objective term to restrict the distortions and introduce an Adaptive Geometry-aware Attack Optimization strategy to adjust attacking strength iteratively based on local geometric frequencies, striking a good balance between stealthiness and attacking accuracy. Moreover, we propose a Bayesian Surrogate Network to enhance transferability and introduce a new metric, the Area Under Accuracy (AUACC), for comprehensive performance evaluation. Experiments on various mesh classifiers demonstrate the effectiveness of our method in both white-box and black-box settings, enhancing the attack stealthiness and transferability across multiple networks. Our research can enhance the understanding of DNNs, thus improving the robustness of mesh classifiers. The code is available at https://github.com/Tengjia-Kang/TPAM.en_US
dc.description.sectionheadersGeometric Processing I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241285
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241285
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241285
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Mesh geometry models; Shape analysis
dc.subjectComputing methodologies → Mesh geometry models
dc.subjectShape analysis
dc.titleTPAM: Transferable Perceptual-constrained Adversarial Meshesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241285.pdf
Size:
5.7 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters