Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation

• URL: http://arxiv.org/abs/2410.15618v2
• Date: Tue, 29 Oct 2024 22:14:49 GMT
• Title: Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
• Authors: Anh Bui, Long Vuong, Khanh Doan, Trung Le, Paul Montague, Tamas Abraham, Dinh Phung,
• Abstract summary: 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.
• Score: 22.3077678575067
• License:
• Abstract: Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A practical solution is to selectively removing target concepts from the model, but this may impact the remaining concepts. Prior approaches have tried to balance this by introducing a loss term to preserve neutral content or a regularization term to minimize changes in the model parameters, yet resolving this trade-off remains challenging. In this work, we propose to identify and preserving concepts most affected by parameter changes, termed as \textit{adversarial concepts}. This approach ensures stable erasure with minimal impact on the other 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 while maintaining the integrity of other unrelated elements. Our code is available at \url{https://github.com/tuananhbui89/Erasing-Adversarial-Preservation}.

Related papers

• SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation [65.30207993362595]
  Unlearning/editing-based methods for safe generation remove harmful concepts from models but face several challenges. We propose SAFREE, a training-free approach for safe T2I and T2V. We detect a subspace corresponding to a set of toxic concepts in the text embedding space and steer prompt embeddings away from this subspace.
  arXiv  Detail & Related papers  (2024-10-16T17:32:23Z)
• 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)
• 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)
• Removing Undesirable Concepts in Text-to-Image Diffusion Models with Learnable Prompts [23.04942433104886]
  We propose a novel method to remove undesirable concepts from text-to-image diffusion models by incorporating a learnable prompt into the cross-attention module. This learnable prompt acts as additional memory, capturing the knowledge of undesirable concepts. We demonstrate the effectiveness of our method on the Stable Diffusion model, showcasing its superiority over state-of-the-art erasure methods.
  arXiv  Detail & Related papers  (2024-03-18T23:42:04Z)
• All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models [22.60023885544265]
  Large-scale datasets may contain sexually explicit, copyrighted, or undesirable content, which allows the model to directly generate them. Fine-tuning algorithms have been developed to tackle concept erasing in diffusion models. We present a new approach that solves all of these challenges.
  arXiv  Detail & Related papers  (2023-12-20T07:04:33Z)
• 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)
• Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion [106.42918868850249]
  We propose a novel strategy named textbfDegeneration-Tuning (DT) to shield contents of unwanted concepts from SD weights. As this adaptation occurs at the level of the model's weights, the SD, after DT, can be grafted onto other conditional diffusion frameworks like ControlNet to shield unwanted concepts.
  arXiv  Detail & Related papers  (2023-08-02T03:34:44Z)
• 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)

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.