Related papers: Robust Concept Erasure in Diffusion Models: A Theo…
Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as…
Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style…
With the rapid growth of text-to-image models, a variety of techniques have been suggested to prevent undesirable image generations. Yet, these methods often only protect against specific user prompts and have been shown to allow unsafe…
Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a challenge known as adjacency. To address this, we propose FADE…
Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable…
Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…
Concerns about text-to-image (T2I) generative models infringing on privacy, copyright, and safety have led to the development of concept erasure techniques (CETs). The goal of an effective CET is to prohibit the generation of undesired…
Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…
The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy,…
Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled reproduction of sensitive, copyrighted, or harmful imagery poses…
Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…
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…
Score-based diffusion models learn to reverse a stochastic differential equation that maps data to noise. However, for complex tasks, numerical error can compound and result in highly unnatural samples. Previous work mitigates this drift…
Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation…
Diffusion-based generative models have become dominant generators of high-fidelity images and videos but remain limited by their computationally expensive inference procedures. Existing acceleration techniques either require extensive model…
Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential…
Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal…
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…
Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright…
Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure methods aim to restrict edits to the spatial region occupied by the target concept.…