相关论文: Unlearning Concepts in Diffusion Model via Concept…

As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. However, when deployed in real-world scenarios, such solutions…

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…

Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how…

Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. <orange-cat> = orange + cat)?…

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

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…

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to…

Text-to-image diffusion models have been demonstrated with undesired generation due to unfiltered large-scale training data, such as sexual images and copyrights, necessitating the erasure of undesired concepts. Most existing methods focus…

Recently, GAN inversion methods combined with Contrastive Language-Image Pretraining (CLIP) enables zero-shot image manipulation guided by text prompts. However, their applications to diverse real images are still difficult due to the…

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often…

Image inpainting aims to fill in the missing pixels with visually coherent and semantically plausible content. Despite the great progress brought from deep generative models, this task still suffers from i. the difficulties in large-scale…

The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads to the problem of machine unlearning (MU), aiming to…

Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A widely used strategy, the gradient difference method, applies…

Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the target concept is absent from generated frames, treating…

Machine Unlearning has recently garnered significant attention, aiming to selectively remove knowledge associated with specific data while preserving the model's performance on the remaining data. A fundamental challenge in this process is…

Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variability and subject-specific differences. This challenge arises…

Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU methods based on label manipulation or model weight perturbations…

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently…

Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However,…