Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer

• URL: http://arxiv.org/abs/2608.20748v1
• Date: Fri, 21 Aug 2026 05:16:50 GMT
• Title: Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
• Abstract summary: Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images.<n> deploying such a high-performance model may expose critical security vulnerabilities.<n>Traditional adversarial perturbations require costly per-scene optimization, while Universal Adrial Perturbations (UAPs) rely on a single static pattern and fail to effectively attack VGGT.<n>We propose textbfMVAP-G, a multi-view adversarial perturbation generator that produces imperceptible consistent perturbations across multiple views in a single feed-forward pass.
• Score: 23.012613078922598
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-performance model may expose critical security vulnerabilities. Traditional adversarial perturbations require costly per-scene optimization, while Universal Adversarial Perturbations (UAPs) rely on a single static pattern and fail to effectively attack VGGT. To address these limitations, we propose \textbf{MVAP-G}, a multi-view adversarial perturbation generator that produces imperceptible consistent perturbations across multiple views in a single feed-forward pass. To ensure perturbation consistency across diverse scenes, we design a cross-view adversarial alignment mechanism to process multi-view images. Experiments demonstrate that MVAP-G significantly degrades VGGT performance without iterative optimization during inference. This work pioneers multi-view adversarial attacks on 3D foundation models, uncovering severe vulnerabilities and underscoring the urgent need for robust 3D vision systems. The code is available at https://github.com/qsong2001/mvap-g.

Related papers

• Diversity-aware View Partitioning for Scalable VGGT [48.654660686945526]
  VGGT achieve strong performance by jointly reasoning over multiple views with global attention.<n>We propose a training-free and plug-and-play inference framework that organizes views into diversity-aware balanced chunks.<n>Our framework also complements existing VGGT variants, enabling scalable multi-view reconstruction without sacrificing geometric fidelity.
  arXiv  Detail & Related papers  (2026-07-02T08:37:56Z)
• Visual Geometry Transformer in the Wild: Distractor-Free 3D Reconstruction [77.75911117889915]
  Current end-to-end multi-view 3D reconstruction methods achieve impressive results, but rely on a restrictive static assumption.<n>This reliance on idealized inputs causes even the most advanced methods to fail in real-world settings.<n>We propose Visual Geometry Transformer in the Wild, an end-to-end framework for robust reconstruction from inconsistent views.
  arXiv  Detail & Related papers  (2026-06-22T02:52:22Z)
• MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation [59.75554954111619]
  We introduce Multi-view 3D Referring Expression (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images.<n>We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning.<n>Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives.
  arXiv  Detail & Related papers  (2026-01-11T11:44:07Z)
• VGGT-DP: Generalizable Robot Control via Vision Foundation Models [13.41554759983567]
  VGGT-DP is a visuomotor policy framework that integrates geometric priors from a pretrained 3D perception model with proprioceptive feedback.<n>We adopt the Visual Geometry Grounded Transformer (VGGT) as the visual encoder and introduce a proprioception-guided visual learning strategy to align perception with internal robot states.<n>Experiments on challenging MetaWorld tasks show that VGGT-DP significantly outperforms strong baselines such as DP and DP3, particularly in precision-critical and long-horizon scenarios.
  arXiv  Detail & Related papers  (2025-09-23T08:15:30Z)
• 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation [50.03578546845548]
  Physical adversarial attack methods expose the vulnerabilities of deep neural networks and pose a significant threat to safety-critical scenarios such as autonomous driving.<n> Camouflage-based physical attack is a more promising approach compared to the patch-based attack, offering stronger adversarial effectiveness in complex physical environments.<n>We propose a physical attack framework based on 3D Gaussian Splatting (3DGS), named PGA, which provides rapid and precise reconstruction with few images.
  arXiv  Detail & Related papers  (2025-07-02T05:10:16Z)
• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos.<n>These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation [1.4680035572775534]
  This paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition. Unlike conventional attacks limited to single views, our approach operates on multiple 2D images, offering a practical and scalable solution.
  arXiv  Detail & Related papers  (2024-04-02T20:29:59Z)
• Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks [53.67497327319569]
  We introduce a novel neural rendering technique to solve image-to-3D from a single view. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
  arXiv  Detail & Related papers  (2023-12-24T08:42:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.