相关论文: When Are Concepts Erased From Diffusion Models?

Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful content. This has fostered a dynamic interplay between the…

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Teaching text-to-image models to be creative involves using style ambiguity loss, which requires a pretrained classifier. In this work, we explore a new form of the style ambiguity training objective, used to approximate creativity, that…

Attribution methods assess the contribution of inputs to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the prediction. Though conceptually simple,…

Text-to-image diffusion models have been demonstrated with undesired generation due to unfiltered large-scale training data, such as sexual images and copyrights, necessitating the erasure of undesired concepts. Most existing methods focus…

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…

While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…

Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of…

Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However,…

Fine-tuning based concept erasing has demonstrated promising results in preventing generation of harmful contents from text-to-image diffusion models by removing target concepts while preserving remaining concepts. To maintain the…

In current AI era, users may request AI companies to delete their data from the training dataset due to the privacy concerns. As a model owner, retraining a model will consume significant computational resources. Therefore, machine…

Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model. However, most existing methods for concept explanations are tailored to specific models. To address this issue, this…

The rapid growth of text-to-image diffusion models has raised concerns about their potential misuse in generating harmful or unauthorized contents. To address these issues, several Concept Erasure methods have been proposed. However, most…

The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious…

Custom diffusion models (CDMs) have attracted widespread attention due to their astonishing generative ability for personalized concepts. However, most existing CDMs unreasonably assume that personalized concepts are fixed and cannot change…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

We call into question the recently popularized method of direct model editing as a means of correcting factual errors in LLM generations. We contrast model editing with three similar but distinct approaches that pursue better defined…

Text-to-image (T2I) diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of these models can inadvertently led they to…

The rapid proliferation of large-scale text-to-image diffusion (T2ID) models has raised serious concerns about their potential misuse in generating harmful content. Although numerous methods have been proposed for erasing undesired concepts…