Related papers: STEREO: A Two-Stage Framework for Adversarially Ro…
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.…
Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted…
Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising…
Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are…
Text-to-image diffusion models (T2I DMs), represented by Stable Diffusion, which generate highly realistic images based on textual input, have been widely used, but their flexibility also makes them prone to misuse for producing harmful or…
Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…
Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed as the "implicit concepts", could be unintentionally learned during training and then be…
Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both…
Recent efforts on scene text erasing have shown promising results. However, existing methods require rich yet costly label annotations to obtain robust models, which limits the use for practical applications. To this end, we study an…
Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…
Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…
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…
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…
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…
Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work)…
Remarkable progress in text-to-image diffusion models has brought a major concern about potentially generating images on inappropriate or trademarked concepts. Concept erasing has been investigated with the goals of deleting target concepts…
As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted characters or styles-has become essential for safety and compliance. Existing unlearning…
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…
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…
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.…