Pith. sign in

REVIEW 1 cited by

Understanding (Un)Intended Memorization in Text-to-Image Generative Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.07550 v1 pith:3SZPKJSI submitted 2023-12-06 cs.CV cs.CLcs.CRcs.LG

classification cs.CVcs.CLcs.CRcs.LG
keywords memorizationmodelstext-to-imagediffusiongenerativeuserdefinitionsdetailed
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Multimodal machine learning, especially text-to-image models like Stable Diffusion and DALL-E 3, has gained significance for transforming text into detailed images. Despite their growing use and remarkable generative capabilities, there is a pressing need for a detailed examination of these models' behavior, particularly with respect to memorization. Historically, memorization in machine learning has been context-dependent, with diverse definitions emerging from classification tasks to complex models like Large Language Models (LLMs) and Diffusion models. Yet, a definitive concept of memorization that aligns with the intricacies of text-to-image synthesis remains elusive. This understanding is vital as memorization poses privacy risks yet is essential for meeting user expectations, especially when generating representations of underrepresented entities. In this paper, we introduce a specialized definition of memorization tailored to text-to-image models, categorizing it into three distinct types according to user expectations. We closely examine the subtle distinctions between intended and unintended memorization, emphasizing the importance of balancing user privacy with the generative quality of the model outputs. Using the Stable Diffusion model, we offer examples to validate our memorization definitions and clarify their application.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models

    cs.CV 2025-04 conditional novelty 5.0 of 10

    PRSS replaces the unconditional anchor in classifier-free guidance with the original prompt and searches for semantically similar alternative prompts, improving the privacy-utility trade-off against memorization baselines.

Pith tools