Metraipolis › archive › dc_ce5bd485229a

Spectral Signatures of Memorization Basins in Diffusion Trajectories — arXiv:2611.01775

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01775
License (as archived)
CC0-1.0
Archived
2026-11-03T18:37:01.828Z
SHA-256 of the archived text
efba20c2b105a3e07e37c1d990105ca43150d17dc54d741c0a3f6eacff5ff188
Stable URL of this page
https://metraipolis.com/documento/dc_ce5bd485229a

How to cite

Spectral Signatures of Memorization Basins in Diffusion Trajectories — arXiv:2611.01775 — arXiv (en), https://arxiv.org/abs/2611.01775 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce5bd485229a (Metraipolis archive dc_ce5bd485229a, sha256 efba20c2b105a3e07e37c1d990105ca43150d17dc54d741c0a3f6eacff5ff188)
BibTeX
@misc{dcce5bd485229a,
  title = {Spectral Signatures of Memorization Basins in Diffusion Trajectories — arXiv:2611.01775},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01775},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce5bd485229a; sha256 efba20c2b105a3e07e37c1d990105ca43150d17dc54d741c0a3f6eacff5ff188},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01775. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01775 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.524Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).