mlsanityData to 7 Oct 2026

SolidMark: Evaluating Image Memorization in Generative Models

arXiv 2503.00592 ↗First posted 1 Mar 2025cs.LGcited by 3

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Recent works have shown that diffusion models are able to memorize training images and emit them at generation time. However, the metrics used to evaluate memorization and its mitigation techniques suffer from dataset-dependent biases and struggle to detect whether a given specific image has been memorized or not. This paper begins with a comprehensive exploration of issues surrounding memorization metrics in diffusion models. Then, to mitigate these issues, we introduce rm stylefont-variant: small-capsSolidMark, a novel evaluation method that provides a per-image memorization score. We then re-evaluate existing memorization mitigation techniques. We also show that rm stylefont-variant: small-capsSolidMark is capable of evaluating fine-grained pixel-level memorization. Finally, we release a variety of models based on rm stylefont-variant: small-capsSolidMark to facilitate further research for understanding memorization phenomena in generative models. All of our code is available at https://github.com/NickyDCFP/SolidMark.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 37 of its 42 references that are in the map. First posted on arXiv 1 Mar 2025.

Builds on

37 of 42 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Detecting, Explaining, and Mitigating Memorization in Diffusion Models31 Jul
  2. 2024Towards Memorization-Free Diffusion Models1 Apr
  3. 2024Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data20 Mar
  4. 2024Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention17 Mar
  5. 2023Understanding (Un)Intended Memorization in Text-to-Image Generative Models6 Dec
  6. 2023Understanding and Mitigating Copying in Diffusion Models31 May
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  8. 2021Membership Inference Attacks From First Principlescited by 839
  9. 2023Extracting Training Data from Diffusion Modelscited by 723
  10. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  11. 2023Erasing Concepts from Diffusion Modelscited by 530
  12. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
17 more
  1. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  2. 2023Unified Concept Editing in Diffusion Modelscited by 377
  3. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  4. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  5. 2024Data Engineering for Scaling Language Models to 128K Contextcited by 183
  6. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  7. 2024Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Modelscited by 150
  8. 2019Robust Invisible Video Watermarking with Attentioncited by 144
  9. 2022Reconstructing Training Data with Informed Adversariescited by 143
  10. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  11. 2024Needle In A Multimodal Haystackcited by 56
  12. 2022Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queriescited by 36
  13. 2024In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Misscited by 36
  14. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  15. 2023Watermarking Diffusion Modelcited by 34
  16. 2024Robust Concept Erasure Using Task Vectorscited by 27
  17. 2024Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Datacited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarkscited by 4
  2. 2025DFA-CON: A Contrastive Learning Approach for Detecting Copyright Infringement in DeepFake Artcited by 0
  3. 2026Secrets Everywhere: Auditing Memorization in Mobility Prediction Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
  2. 2026The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
  3. 2024Exploring Local Memorization in Diffusion Models via Bright Ending Attention
  4. 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
  5. 2025Finding DoRI: Discovery of Retained Images in Diffusion Models
  6. 2024MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models
  7. 2023Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication
  8. 2025Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models