cs.LGNov 1, 2026

Spectral Signatures of Memorization Basins in Diffusion Trajectories

Authors: Achref Jaziri, Martin Mundt, Ahmed Imtiaz Humayun, Visvanthan Ramesh

Organizations: Goethe University Frankfurt, Frankfurt am Main, Germany · University of Bremen, Bremen, Germany · Google, New York, NY, USA

Abstract

Diffusion models are known to reproduce individual examples from their training data as a form of memorization with implications for generalization, privacy, and downstream use. Recent work demonstrated that memorized training samples reside inside contiguous regions of the data/latent space known as basins of memorization -- once a denoising trajectory enters a basin, under finite perturbations it irreversibly reproduces a memorized example. Prior empirical work on such basins in trained models has primarily focused on classifier-free guidance based detection and mitigation strategies in text-to-image models, leaving basin entry and their formation largely uncharacterized. In this paper, we present a geometric characterization of memorization basins for conditional, unconditional, and rectified-flow-based diffusion models. We observe a characteristic signature in the local spectrum of the function geometry that distinguishes basin entry: the emergence of a dominant singular mode followed by a sharp spectral recovery. This signature appears at two timescales: along denoising trajectories during inference and over the course of training. We further investigate whether these geometric signatures can be used to intervene on memorization. During training, we suppress memorization by acting on the dominant mode. At inference, we develop methods to identify trajectories entering memorization basins and steer them away. We find that these interventions remain effective even with low-dimensional approximations of the underlying geometry, and demonstrate that geometry-informed steering extends to large-scale text-to-image diffusion models. Together, our results corroborate that local spectral geometry provides a common basis for characterizing memorization and for suppressing, detecting, and steering away from it across training and generation.

Figures & tables

Appendix figures & tables25 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising

    Oct 8, 2026Nikhil Verma, Siddharthan Dileep, Anoop Singh +4Memorization in Generative ModelsDiffusion Models

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

    May 26, 2026Gwangho Kim, Sungyoon LeeMemorization in Generative ModelsDiffusion Models

  3. Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models

    Feb 19, 2026Nick Dodson, Xinyu Gao, Qingsong Wang +2Memorization in Generative ModelsDiffusion Models