Related papers: Differential Vector Erasure: Unified Training-Free…
The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous…
Studies have been conducted to prevent specific concepts from being generated from pretrained text-to-image generative models, achieving concept erasure in various ways. However, the performance evaluation of these studies is still largely…
Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods,…
Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…
We propose a novel PDE-driven corruption process for generative image synthesis based on advection-diffusion processes which generalizes existing PDE-based approaches. Our forward pass formulates image corruption via a physically motivated…
Concept erasure is extensively utilized in image generation to prevent text-to-image models from generating undesired content. Existing methods can effectively erase narrow concepts that are specific and concrete, such as distinct…
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off. Robustness means the model fine-tuned by concept erasure methods resists reactivation of erased…
Concept erasure has emerged as a promising approach to mitigate undesired or unsafe content in diffusion models, yet existing methods still face significant limitations. While training-based methods are effective, their high computational…
The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous…
Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised significant safety and copyright concerns. Efforts to address these…
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand,…
Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real image using…
Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…
Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. Although various techniques have been proposed to mitigate unwanted influences…
Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright…
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…
Editing images with diffusion models under strict training-free constraints remains a significant challenge. While recent optimisation-based methods achieve strong zero-shot edits from text, they struggle to preserve identity and capture…
Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…
Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…
The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure…