Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences

• URL: http://arxiv.org/abs/2605.26756v2
• Date: Thu, 28 May 2026 16:35:20 GMT
• Title: Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
• Abstract summary: Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright.<n>We provide a geometric characterization of local memorization as a coordinate-wise variance collapse.<n>We derive a score-difference proxy that provides a geometric explanation for the widely used score-difference-based detection metric.
• Score: 7.519872646378835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models can unintentionally memorize training samples, raising concerns about privacy and copyright. While recent methods can detect memorization, they often rely on global or model-specific signals and provide limited insight into where memorization appears within a generated image. We provide a geometric characterization of local memorization as a coordinate-wise variance collapse. However, such collapse can also arise from intrinsic data constraints rather than overfitting. To isolate overfitting-driven memorization, we propose curvature-difference methods that subtract the curvature of an underfitted baseline, either the unconditional model or a less-trained version of itself. We further derive a score-difference proxy that provides a geometric explanation for the widely used score-difference-based detection metric. Experiments on Stable Diffusion, evaluated against ground-truth memorization masks, show that our method outperforms the prior attention-based localization method. Code is available at https://github.com/Gwangho99/mem-curv-diff.

Related papers

• Local Coverage Governs Memorization in Diffusion Models [10.085837353469737]
  We show that memorization is governed by emphlocal data coverage.<n>We show that classes with higher intra-class sparsity (and thus lower local coverage) are more strongly memorized.
  arXiv  Detail & Related papers  (2026-06-12T12:25:13Z)
• Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects [17.220195638215507]
  Diffusion language models (DLMs) have emerged as a competitive alternative to autoregressive language models (ARMs)<n>DLMs exhibit substantially lower memorization-based leakage of personally identifiable information (PII) compared to ARMs.
  arXiv  Detail & Related papers  (2026-03-02T19:03:32Z)
• Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability [9.133729396364952]
  Diffusion-based image generative models produce high-fidelity images through iterative denoising but remain vulnerable to memorization.<n>Recent memorization detection methods are primarily based on the norm of score difference as indicators of memorization.<n>We develop a memorization detection metric by integrating isotropic norm and anisotropic alignment.
  arXiv  Detail & Related papers  (2026-01-28T14:29:42Z)
• Provable Separations between Memorization and Generalization in Diffusion Models [31.32606216124959]
  We develop a dual-separation result via statistical estimation and network approximation.<n>We show that the ground-truth score function does not minimize the empirical denoising loss, creating a separation that drives memorization.
  arXiv  Detail & Related papers  (2025-11-05T05:37:57Z)
• Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency [52.52950138164424]
  We show that when leveraging the off-the-shelf (vision) foundation models for feature extraction, the geometric shapes of the resulting feature distributions exhibit remarkable transferability across domains and datasets.<n>We embody our geometric knowledge-guided distribution calibration framework in two popular and challenging settings: federated learning and long-tailed recognition.<n>In long-tailed learning, it utilizes the geometric knowledge transferred from sample-rich categories to recover the true distribution for sample-scarce tail classes.
  arXiv  Detail & Related papers  (2025-08-19T05:22:59Z)
• Demystifying Foreground-Background Memorization in Diffusion Models [23.914702151370204]
  Diffusion models (DMs) memorize training images and can reproduce near-duplicates during generation.<n>Current detection methods identify verbatim memorization but fail to capture two critical aspects.<n>We propose Foreground Background Memorization (FB-Mem), a novel segmentation-based metric that classifies and quantifies memorized regions within generated images.
  arXiv  Detail & Related papers  (2025-08-16T20:15:16Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models [63.1637853118899]
  We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. We employ a shift control module that works on h-space of pre-trained diffusion models to manipulate a sample into a shifted version of itself. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions.
  arXiv  Detail & Related papers  (2023-10-15T18:44:30Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)

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.