VoxShield: Protecting 3D Medical Datasets from Unauthorized Training via Frequency-Aware Inter-Slice Disruption

• URL: http://arxiv.org/abs/2605.17345v1
• Date: Sun, 17 May 2026 09:35:19 GMT
• Title: VoxShield: Protecting 3D Medical Datasets from Unauthorized Training via Frequency-Aware Inter-Slice Disruption
• Abstract summary: Unlearnable Examples (UE) offer protection by injecting imperceptible perturbations to prevent effective model learning.<n>We propose VoxShield, a UE framework that explicitly targets the inductive biases of 3D networks.<n> Experiments on BraTS19 and FLARE21 demonstrate that VoxShield successfully degrades 3D segmentation performance.
• Score: 25.533159285300176
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The release of public 3D medical image segmentation (MIS) datasets accelerates clinical research but simultaneously heightens risks of unauthorized AI model training. While Unlearnable Examples (UE) offer protection by injecting imperceptible perturbations to prevent effective model learning, existing methods primarily target 2D scenarios. They neglect the volumetric spatial correlations and inter-slice anatomical consistency inherent in 3D medical volumes, which serve as critical learning priors for 3D segmentation networks. To bridge this gap, we propose VoxShield, a UE framework that explicitly targets the volumetric inductive biases of 3D networks. Our core insight is that by systematically dismantling the cross-slice continuity that 3D architectures rely on, we can fundamentally impair their spatial aggregation process. Specifically, we introduce an Inter-Slice Frequency Consistency Disruption mechanism that maximizes the spectral divergence between adjacent slices, injecting structural incoherence along the $z$-axis. Complementing this structural attack, a Semantic Prediction Disruption module is incorporated. By maximizing the $\ell_1$ divergence between clean and perturbed logits, it forces the injected noise to penetrate the entire network and corrupt the final semantic mapping. Experiments on BraTS19 and FLARE21 demonstrate that VoxShield successfully degrades 3D segmentation performance, reducing the DSC from 80.0% to near 0.0% and from 88.6% to 6.8%, respectively. All protections are achieved with minimal perturbation ($ε=4/255$) to preserve high visual fidelity. The code is available at https://github.com/KK266299/VoxShield.

Related papers

• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections [54.51153206716027]
  Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server.<n>We propose LightSplit, which limits information exposure and reduces communication overhead by applying a lightweight fixed random projection at the cut layer.<n>Our results show that the method retains more than 95% of the baseline accuracy at up to 32x reduction in transmitted dimensionality.
  arXiv  Detail & Related papers  (2026-05-13T09:45:49Z)
• Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data [1.38067449150135]
  Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation.<n>We analyze divergent regularization needs for multi-class segmentation of high-resolution ex vivo spinal cord MRI.
  arXiv  Detail & Related papers  (2026-05-12T21:06:53Z)
• Structure-Adaptive Sparse Diffusion in Voxel Space for 3D Medical Image Enhancement [10.028882244604809]
  Three-dimensional (3D) medical image enhancement, including denoising and super-resolution, is critical for clinical diagnosis in CT, PET, and MRI.<n>We propose a sparse voxel-space diffusion framework that trains and samples on a compact set of uniformly subsampled timesteps.<n>Our framework preserves fine anatomical detail without lossy compression while achieving up to $10times$ training acceleration.
  arXiv  Detail & Related papers  (2026-04-20T03:52:49Z)
• Anatomy Aware Cascade Network: Bridging Epistemic Uncertainty and Geometric Manifold for 3D Tooth Segmentation [13.650721192161079]
  We propose the Anatomy Aware Cascade Network (AACNet) to resolve boundary ambiguity and maintain global structural consistency.<n>We show that AACNet achieves a Dice Similarity Coefficient of 90.17 % and a 95% Hausdorff Distance of 3.63 mm, significantly outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-01-12T12:53:27Z)
• JanusNet: Hierarchical Slice-Block Shuffle and Displacement for Semi-Supervised 3D Multi-Organ Segmentation [8.81080587136333]
  We propose JanusNet, a data augmentation framework for 3D medical data.<n>Our Slice-Block Shuffle step shuffles same-index slice blocks across volumes along a random axis.<n>Our Confidence-Guided Displacement step uses prediction reliability to replace blocks within each slice, amplifying signals from difficult areas.
  arXiv  Detail & Related papers  (2025-08-06T01:08:02Z)
• Toward Availability Attacks in 3D Point Clouds [28.496421433836908]
  We show that extending 2D availability attacks directly to 3D point clouds under distance regularization is susceptible to the degeneracy. We propose a novel Feature Collision Error-Minimization (FC-EM) method, which creates additional shortcuts in the feature space. Experiments on typical point cloud datasets, 3D intracranial aneurysm medical dataset, and 3D face dataset verify the superiority and practicality of our approach.
  arXiv  Detail & Related papers  (2024-06-26T08:13:30Z)
• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.<n>We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• 3D Adversarial Augmentations for Robust Out-of-Domain Predictions [115.74319739738571]
  We focus on improving the generalization to out-of-domain data. We learn a set of vectors that deform the objects in an adversarial fashion. We perform adversarial augmentation by applying the learned sample-independent vectors to the available objects when training a model.
  arXiv  Detail & Related papers  (2023-08-29T17:58:55Z)
• 3-Dimensional Deep Learning with Spatial Erasing for Unsupervised Anomaly Segmentation in Brain MRI [55.97060983868787]
  We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance. We compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE.
  arXiv  Detail & Related papers  (2021-09-14T09:17:27Z)

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.