Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted

• URL: http://arxiv.org/abs/2406.18566v1
• Date: Sat, 1 Jun 2024 15:47:13 GMT
• Title: Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted
• Authors: Ruchika Chavhan, Ondrej Bohdal, Yongshuo Zong, Da Li, Timothy Hospedales,
• Abstract summary: Large-scale text-to-image diffusion models excel in generating high-quality images from textual inputs. Concerns arise as research indicates their tendency to memorize and replicate training data. Efforts within the text-to-image community to address memorization explore causes such as data duplication, replicated captions, or trigger tokens.
• Score: 15.162296378581853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale text-to-image diffusion models excel in generating high-quality images from textual inputs, yet concerns arise as research indicates their tendency to memorize and replicate training data, raising We also addressed the issue of memorization in diffusion models, where models tend to replicate exact training samples raising copyright infringement and privacy issues. Efforts within the text-to-image community to address memorization explore causes such as data duplication, replicated captions, or trigger tokens, proposing per-prompt inference-time or training-time mitigation strategies. In this paper, we focus on the feed-forward layers and begin by contrasting neuron activations of a set of memorized and non-memorized prompts. Experiments reveal a surprising finding: many different sets of memorized prompts significantly activate a common subspace in the model, demonstrating, for the first time, that memorization in the diffusion models lies in a special subspace. Subsequently, we introduce a novel post-hoc method for editing pre-trained models, whereby memorization is mitigated through the straightforward pruning of weights in specialized subspaces, avoiding the need to disrupt the training or inference process as seen in prior research. Finally, we demonstrate the robustness of the pruned model against training data extraction attacks, thereby unveiling new avenues for a practical and one-for-all solution to memorization.

Related papers

• Detecting, Explaining, and Mitigating Memorization in Diffusion Models [49.438362005962375]
  We introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions. Our proposed method seamlessly integrates without disrupting sampling algorithms, and delivers high accuracy even at the first generation step. Building on our detection strategy, we unveil an explainable approach that shows the contribution of individual words or tokens to memorization.
  arXiv  Detail & Related papers  (2024-07-31T16:13:29Z)
• Could It Be Generated? Towards Practical Analysis of Memorization in Text-To-Image Diffusion Models [39.607005089747936]
  We perform practical analysis of memorization in text-to-image diffusion models. We identify three necessary conditions of memorization, respectively similarity, existence and probability. We then reveal the correlation between the model's prediction error and image replication.
  arXiv  Detail & Related papers  (2024-05-09T15:32:00Z)
• Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention [62.671435607043875]
  Research indicates that text-to-image diffusion models replicate images from their training data, raising tremendous concerns about potential copyright infringement and privacy risks. We reveal that during memorization, the cross-attention tends to focus disproportionately on the embeddings of specific tokens. We introduce an innovative approach to detect and mitigate memorization in diffusion models.
  arXiv  Detail & Related papers  (2024-03-17T01:27:00Z)
• Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication [16.447035745151428]
  Diffusion-based models have revolutionized text-to-image synthesis with their ability to produce high-quality, high-resolution images. These models also raise concerns due to their tendency to replicate exact training samples, posing privacy risks and enabling adversarial attacks. This paper focuses on two distinct and underexplored types of duplication that lead to replication during inference in diffusion-based models.
  arXiv  Detail & Related papers  (2023-12-06T18:54:44Z)
• Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks [64.67735676127208]
  Text-to-image diffusion models have shown great potential for benefiting image recognition. Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images. We introduce customized solutions by fully exploiting the aforementioned free attention masks.
  arXiv  Detail & Related papers  (2023-08-13T10:07:46Z)
• Understanding and Mitigating Copying in Diffusion Models [53.03978584040557]
  Images generated by diffusion models like Stable Diffusion are increasingly widespread. Recent works and even lawsuits have shown that these models are prone to replicating their training data, unbeknownst to the user.
  arXiv  Detail & Related papers  (2023-05-31T17:58:02Z)
• Measures of Information Reflect Memorization Patterns [53.71420125627608]
  We show that the diversity in the activation patterns of different neurons is reflective of model generalization and memorization. Importantly, we discover that information organization points to the two forms of memorization, even for neural activations computed on unlabelled in-distribution examples.
  arXiv  Detail & Related papers  (2022-10-17T20:15:24Z)
• Counterfactual Memorization in Neural Language Models [91.8747020391287]
  Modern neural language models that are widely used in various NLP tasks risk memorizing sensitive information from their training data. An open question in previous studies of language model memorization is how to filter out "common" memorization. We formulate a notion of counterfactual memorization which characterizes how a model's predictions change if a particular document is omitted during training.
  arXiv  Detail & Related papers  (2021-12-24T04:20:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.