AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models

• URL: http://arxiv.org/abs/2603.23686v1
• Date: Tue, 24 Mar 2026 19:48:23 GMT
• Title: AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models
• Abstract summary: 3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction.<n>Recently emerged feed-forward 3DGS models address these limitations by enabling fast reconstruction from a few input views after large-scale pretraining.<n>We introduce AdvSplat, the first systematic study of adversarial attacks on feed-forward 3DGS.
• Score: 16.115612700186023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction. However, its per-scene optimization pipeline limits scalability and generalization, and prevents efficient inference. Recently emerged feed-forward 3DGS models address these limitations by enabling fast reconstruction from a few input views after large-scale pretraining, without scene-specific optimization. Despite their advantages and strong potential for commercial deployment, the use of neural networks as the backbone also amplifies the risk of adversarial manipulation. In this paper, we introduce AdvSplat, the first systematic study of adversarial attacks on feed-forward 3DGS. We first employ white-box attacks to reveal fundamental vulnerabilities of this model family. We then develop two improved, practically relevant, query-efficient black-box algorithms that optimize pixel-space perturbations via a frequency-domain parameterization: one based on gradient estimation and the other gradient-free, without requiring any access to model internals. Extensive experiments across multiple datasets demonstrate that AdvSplat can significantly disrupt reconstruction results by injecting imperceptible perturbations into the input images. Our findings surface an overlooked yet urgent problem in this domain, and we hope to draw the community's attention to this emerging security and robustness challenge.

Related papers

• PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur [9.855875137621622]
  We address the inverse problem of blind 3D scene reconstruction from extremely motion-red images.<n>Existing approaches typically circumvent this bottleneck by relying on impractical sharp-image supervision.<n>We introduce PRISM3D, a unified framework enabling robust reconstruction directly from severely degraded inputs.
  arXiv  Detail & Related papers  (2026-07-04T12:45:11Z)
• REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance [58.94345609736356]
  REFINE is a highly accelerated 3DGS pruning framework centered on a novel rendering-free primitive importance metric.<n>Experiments across multiple benchmark datasets demonstrate that REFINE maintains highly competitive rendering quality.
  arXiv  Detail & Related papers  (2026-06-08T06:16:38Z)
• ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting [65.02700555625749]
  ForeSplat is an optimization-aware training framework for feed-forward 3DGS models.<n>ForeSplat substantially reduces the capacity pressure on the feed-forward model.<n>It bridges the gap between amortized prediction and per-scene optimization.
  arXiv  Detail & Related papers  (2026-05-21T05:38:47Z)
• GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views [44.787835922271135]
  GIFSplat is a purely feed-forward iterative refinement framework for 3D Gaussian refineting from sparse unposed views.<n>It consistently outperforms state-of-the-art feed-forward baselines across DL3DV, RealEstate10K, and DTU.<n>It maintains second-scale inference time without requiring camera poses or any test-time gradient optimization.
  arXiv  Detail & Related papers  (2026-02-26T03:25:18Z)
• DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering [16.115612700186023]
  3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images.<n>Recent studies reveal its vulnerability to adversarial corruptions in input views, where imperceptible yet consistent perturbations can drastically degrade rendering quality.<n>We propose a frequency-aware defense strategy that reconstructs training views by filtering high-frequency noise while preserving low-frequency content.
  arXiv  Detail & Related papers  (2026-02-22T20:00:02Z)
• RobustSplat++: Decoupling Densification, Dynamics, and Illumination for In-the-Wild 3DGS [85.90134051583368]
  3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling in-the-wild scenes affected by transient objects and illuminations.<n>We propose RobustSplat++, a robust solution based on several critical designs.
  arXiv  Detail & Related papers  (2025-12-04T14:05:09Z)
• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [79.15416002879239]
  3D Gaussian Splatting has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images.<n>We propose RobustSplat, a robust solution based on two critical designs.
  arXiv  Detail & Related papers  (2025-06-03T11:13:48Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction [50.534213038479926]
  FreeSplat++ is an alternative approach to large-scale indoor whole-scene reconstruction.<n>Our method with depth-regularized per-scene fine-tuning demonstrates substantial improvements in reconstruction accuracy and a notable reduction in training time.
  arXiv  Detail & Related papers  (2025-03-29T06:22:08Z)
• SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction [45.654397516679495]
  This paper is the first to categorize 3DGS pruning techniques into two types: Scene-level pruning and Pixel-level pruning. Experiments show that pixel-level pruning provides an inherent boundary of pruning, i.e., a safeguard of Gaussian pruning. We believe our research provides valuable insights for optimizing 3DGS for future works.
  arXiv  Detail & Related papers  (2024-05-28T03:41:36Z)

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.