Papers
arxiv:2507.16880

Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed

Published on Jul 22
· Submitted by lukas-struppek on Jul 24
Authors:
,
,
,

Abstract

Pruning-based defenses in text-to-image diffusion models are ineffective as minor adjustments to text embeddings can re-trigger data replication, necessitating methods that truly remove memorized content.

AI-generated summary

Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potential to inadvertently memorize and replicate training data. Recent mitigation efforts have focused on identifying and pruning weights responsible for triggering replication, based on the assumption that memorization can be localized. Our research assesses the robustness of these pruning-based approaches. We demonstrate that even after pruning, minor adjustments to text embeddings of input prompts are sufficient to re-trigger data replication, highlighting the fragility of these defenses. Furthermore, we challenge the fundamental assumption of memorization locality, by showing that replication can be triggered from diverse locations within the text embedding space, and follows different paths in the model. Our findings indicate that existing mitigation strategies are insufficient and underscore the need for methods that truly remove memorized content, rather than attempting to suppress its retrieval. As a first step in this direction, we introduce a novel adversarial fine-tuning method that iteratively searches for replication triggers and updates the model to increase robustness. Through our research, we provide fresh insights into the nature of memorization in text-to-image DMs and a foundation for building more trustworthy and compliant generative AI.

Community

Paper author Paper submitter

https://arxiv.org/abs/2507.16880

Happy to hear your thoughts :)

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.16880 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.16880 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.16880 in a Space README.md to link it from this page.

Collections including this paper 2