相关论文: Side Effects of Erasing Concepts from Diffusion Mo…

With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…

Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typically…

Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to produce harmful or undesirable content. While concept erasure…

Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…

Expressive neural text-to-speech (TTS) systems incorporate a style encoder to learn a latent embedding as the style information. However, this embedding process may encode redundant textual information. This phenomenon is called content…

Concept bottleneck models (CBMs) are interpretable models that first predict a set of semantically meaningful features, i.e., concepts, from observations that are subsequently used to condition a downstream task. However, the model's…

A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wide array of target…

Text-to-Image (T2I) models excel at synthesizing concepts such as nouns, appearances, and styles. To enable customized content creation based on a few example images of a concept, methods such as Textual Inversion and DreamBooth invert the…

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…

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…

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…

In recent years, text-to-image (T2I) generation models have made significant progress in generating high-quality images that align with text descriptions. However, these models also face the risk of unsafe generation, potentially producing…

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to…

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…

Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods offer a promising solution, existing finetuning-based…

The rapid advancement of generative AI highlights the importance of text-to-image (T2I) security, particularly with the threat of backdoor poisoning. Timely disclosure and mitigation of security vulnerabilities in T2I models are crucial for…

Deepfake content on social networks is increasingly produced through multiple \emph{sequential} edits to biometric data such as facial imagery. Consequently, the final appearance of an image often reflects a latent chain of operations…

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…

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…

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…