Related papers: Separable Multi-Concept Erasure from Diffusion Mod…
Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on…
Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their…
Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing…
While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety and ethical risks. These concerns have led to growing interest in concept erasure, the…
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,…
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…
Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…
In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly these approaches remove the target concept from the model.…
As Text-to-Image models continue to evolve, so does the risk of generating unsafe, copyrighted, or privacy-violating content. Existing safety interventions - ranging from training data curation and model fine-tuning to inference-time…
Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable.…
Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models by selectively unlearning undesirable concepts. The common principle of previous works to remove a specific…
Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often…
Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which leads to various ethical and business risks. Specifically,…
Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…
Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods share a common weakness: erased concepts return when the…
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…
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,…
Text-to-image diffusion models may generate harmful or copyrighted content, motivating research on concept erasure. However, existing approaches primarily focus on erasing concepts from text prompts, overlooking other input modalities that…
How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlearning', a novel paradigm that enables the targeted removal of…
Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…