# Filtering Memorization from Parameter-Space in Diffusion Models

arXiv: https://arxiv.org/abs/2605.10439 · HTML: https://mlsanity.com/paper/2605.10439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [On Memorization in Diffusion Models](https://mlsanity.com/paper/2310.02664/) (2023)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Detecting, Explaining, and Mitigating Memorization in Diffusion Models](https://mlsanity.com/paper/2407.21720/) (2024)
- [Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention](https://mlsanity.com/paper/2403.11052/) (2024)
- [Towards Memorization-Free Diffusion Models](https://mlsanity.com/paper/2404.00922/) (2024)
- [A Geometric Framework for Understanding Memorization in Generative Models](https://mlsanity.com/paper/2411.00113/) (2024)
- [Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models](https://mlsanity.com/paper/2406.02366/) (2024)
- [Classifier-Free Guidance inside the Attraction Basin May Cause Memorization](https://mlsanity.com/paper/2411.16738/) (2024)
- [Differentially Private Fine-Tuning of Diffusion Models](https://mlsanity.com/paper/2406.01355/) (2024)
- [Exploring Local Memorization in Diffusion Models via Bright Ending Attention](https://mlsanity.com/paper/2410.21665/) (2024)
- [Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted](https://mlsanity.com/paper/2406.18566/) (2024)

## Abstract (arXiv)

Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter updates. However, LoRAs can memorize training images, causing generated outputs to reproduce copyrighted or sensitive content. This risk is particularly concerning in LoRA-sharing ecosystems, where users distribute trained LoRAs without releasing the underlying training data. Existing approaches for mitigating memorization rely on access to the training pipeline, training data, or control over the inference process, making them difficult to apply when only the released LoRA weights are available. We propose Base-Anchored Filtering (BAF), a training-free and data-free framework for post-hoc memorization mitigation in diffusion LoRAs. BAF decomposes LoRA updates into spectral channels and measures their alignment with the principal subspace of the pretrained backbone. Channels strongly aligned with this subspace are retained as generalizable adaptations, while weakly aligned channels are suppressed as potential carriers of memorized content. Experiments on multiple datasets and diffusion backbones demonstrate that BAF consistently reduces memorization while preserving or even improving generation quality. Our code is available in the supplementary material.