Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts

• URL: http://arxiv.org/abs/2403.12326v3
• Date: Mon, 17 Feb 2025 00:34:04 GMT
• Title: Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts
• Authors: Anh Bui, Khanh Doan, Trung Le, Paul Montague, Tamas Abraham, Dinh Phung,
• Abstract summary: We introduce a novel concept-hiding approach that makes unwanted concepts inaccessible to public users.<n>Instead of erasing knowledge from the model entirely, we incorporate a learnable prompt into the cross-attention module.<n>This enables flexible access control -- ensuring that undesirable content cannot be easily generated while preserving the option to reinstate it.
• Score: 23.04942433104886
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Diffusion models have demonstrated remarkable capability in generating high-quality visual content from textual descriptions. However, since these models are trained on large-scale internet data, they inevitably learn undesirable concepts, such as sensitive content, copyrighted material, and harmful or unethical elements. While previous works focus on permanently removing such concepts, this approach is often impractical, as it can degrade model performance and lead to irreversible loss of information. In this work, we introduce a novel concept-hiding approach that makes unwanted concepts inaccessible to public users while allowing controlled recovery when needed. Instead of erasing knowledge from the model entirely, we incorporate a learnable prompt into the cross-attention module, acting as a secure memory that suppresses the generation of hidden concepts unless a secret key is provided. This enables flexible access control -- ensuring that undesirable content cannot be easily generated while preserving the option to reinstate it under restricted conditions. Our method introduces a new paradigm where concept suppression and controlled recovery coexist, which was not feasible in prior works. We validate its effectiveness on the Stable Diffusion model, demonstrating that hiding concepts mitigate the risks of permanent removal while maintaining the model's overall capability.

Related papers

• Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization [20.783312940122297]
  Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting is necessary. We propose textbfDynamic Mask coupled with Concept-Aware Loss, a novel unlearning framework designed for multi-concept forgetting.
  arXiv  Detail & Related papers  (2025-04-12T01:38:58Z)
• SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders [4.013156524547073]
  Diffusion models can inadvertently generate harmful or undesirable content. Recent machine unlearning approaches offer potential solutions but often lack transparency. We introduce SAeUron, a novel method leveraging features learned by sparse autoencoders.
  arXiv  Detail & Related papers  (2025-01-29T23:29:47Z)
• Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction [88.18235230849554]
  Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. We leverage safe embeddings and a modified diffusion process with weighted tunable summation in the latent space to generate safer images. We identify trade-offs between safety and censorship, which presents a necessary perspective in the development of ethical AI models.
  arXiv  Detail & Related papers  (2024-11-21T09:47:13Z)
• How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization? [91.49559116493414]
  We propose a novel Concept-Incremental text-to-image Diffusion Model (CIDM) It can resolve catastrophic forgetting and concept neglect to learn new customization tasks in a concept-incremental manner. Experiments validate that our CIDM surpasses existing custom diffusion models.
  arXiv  Detail & Related papers  (2024-10-23T06:47:29Z)
• Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation [22.3077678575067]
  Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. We propose to identify and preserving concepts most affected by parameter changes, termed as textitadversarial concepts. We demonstrate the effectiveness of our method using the Stable Diffusion model, showing that it outperforms state-of-the-art erasure methods in eliminating unwanted content.
  arXiv  Detail & Related papers  (2024-10-21T03:40:29Z)
• EIUP: A Training-Free Approach to Erase Non-Compliant Concepts Conditioned on Implicit Unsafe Prompts [32.590822043053734]
  Non-toxic text still carries a risk of generating non-compliant images, which is referred to as implicit unsafe prompts. We propose a simple yet effective approach that incorporates non-compliant concepts into an erasure prompt. Our method exhibits superior erasure effectiveness while achieving high scores in image fidelity.
  arXiv  Detail & Related papers  (2024-08-02T05:17:14Z)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)
• Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [51.931083971448885]
  We propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
  arXiv  Detail & Related papers  (2024-07-17T05:21:41Z)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• Pruning for Robust Concept Erasing in Diffusion Models [27.67237515704348]
  We introduce a new pruning-based strategy for concept erasing. Our method selectively prunes critical parameters associated with the concepts targeted for removal, thereby reducing the sensitivity of concept-related neurons. Experimental results show a significant enhancement in our model's ability to resist adversarial inputs.
  arXiv  Detail & Related papers  (2024-05-26T11:42:20Z)
• Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models [86.92711729969488]
  We analyze how to manipulate the text embeddings and remove unwanted content from them. The first regularizes the text embedding matrix and effectively suppresses the undesired content. The second method aims to further suppress the unwanted content generation of the prompt, and encourages the generation of desired content.
  arXiv  Detail & Related papers  (2024-02-08T03:15:06Z)
• Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers [24.64639078273091]
  Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. We propose Reliable Concept Erasing via Lightweight Erasers (Receler)
  arXiv  Detail & Related papers  (2023-11-29T15:19:49Z)
• Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? [52.238883592674696]
  Ring-A-Bell is a model-agnostic red-teaming tool for T2I diffusion models. It identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T02:11:20Z)
• Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models [63.20512617502273]
  We propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. Our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality.
  arXiv  Detail & Related papers  (2023-07-12T07:48:29Z)
• Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models [79.50701155336198]
  textbfForget-Me-Not is designed to safely remove specified IDs, objects, or styles from a well-configured text-to-image model in as little as 30 seconds. We demonstrate that Forget-Me-Not can effectively eliminate targeted concepts while maintaining the model's performance on other concepts. It can also be adapted as a lightweight model patch for Stable Diffusion, allowing for concept manipulation and convenient distribution.
  arXiv  Detail & Related papers  (2023-03-30T17:58:11Z)
• Ablating Concepts in Text-to-Image Diffusion Models [57.9371041022838]
  Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. These models are typically trained on an enormous amount of Internet data, often containing copyrighted material, licensed images, and personal photos. We propose an efficient method of ablating concepts in the pretrained model, preventing the generation of a target concept.
  arXiv  Detail & Related papers  (2023-03-23T17:59:42Z)

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.