Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient

• URL: http://arxiv.org/abs/2405.15304v2
• Date: Fri, 20 Dec 2024 08:23:46 GMT
• Title: Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
• Authors: Yongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang, Heng Chang, Wenbo Zhu, Xinting Hu, Xiao Zhou, Xu Yang,
• Abstract summary: We propose a novel concept domain correction framework named textbfDoCo (textbfDomaintextbfCorrection) By aligning the output domains of sensitive and anchor concepts through adversarial training, our approach ensures comprehensive unlearning of target concepts. We also introduce a concept-preserving gradient surgery technique that mitigates conflicting gradient components, thereby preserving the model's utility while unlearning specific concepts.
• Score: 20.698305103879232
• License:
• Abstract: 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 solution to eliminate sensitive concepts from these models. Despite its potential, existing MU methods face two main challenges: 1) limited generalization, where concept erasure is effective only within the unlearned set, failing to prevent sensitive concept generation from out-of-set prompts; and 2) utility degradation, where removing target concepts significantly impacts the model's overall performance. To address these issues, we propose a novel concept domain correction framework named \textbf{DoCo} (\textbf{Do}main \textbf{Co}rrection). By aligning the output domains of sensitive and anchor concepts through adversarial training, our approach ensures comprehensive unlearning of target concepts. Additionally, we introduce a concept-preserving gradient surgery technique that mitigates conflicting gradient components, thereby preserving the model's utility while unlearning specific concepts. Extensive experiments across various instances, styles, and offensive concepts demonstrate the effectiveness of our method in unlearning targeted concepts with minimal impact on related concepts, outperforming previous approaches even for out-of-distribution prompts.

Related papers

• Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them [21.386640828092524]
  Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models. We propose the Adaptive Guided Erasure (AGE) method, which emphdynamically selects optimal target concepts tailored to each undesirable concept. Results show that AGE significantly outperforms state-of-the-art erasure methods on preserving unrelated concepts while maintaining effective erasure performance.
  arXiv  Detail & Related papers  (2025-01-31T08:17:23Z)
• Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization [48.20360860166279]
  Large-scale diffusion models produce high-quality images but often generate unwanted content, such as sexually explicit or violent content. We propose a novel approach for targeted concept replacing in diffusion models, enabling specific concepts to be removed without affecting non-target areas. Our method introduces a dedicated concept localizer for precisely identifying the target concept during the denoising process, trained with few-shot learning to require minimal labeled data. Within the identified region, we introduce a training-free Dual Prompts Cross-Attention (DPCA) module to substitute the target concept, ensuring minimal disruption to surrounding content.
  arXiv  Detail & Related papers  (2024-12-02T08:05:39Z)
• Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [51.931083971448885]
  We propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
  arXiv  Detail & Related papers  (2024-07-17T05:21:41Z)
• ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction [20.43411883845885]
  We introduce a novel task named Unsupervised Concept Extraction (UCE) that considers an unsupervised setting without any human knowledge of the concepts. Given an image that contains multiple concepts, the task aims to extract and recreate individual concepts solely relying on the existing knowledge from pretrained diffusion models. We present ConceptExpress that tackles UCE by unleashing the inherent capabilities of pretrained diffusion models in two aspects.
  arXiv  Detail & Related papers  (2024-07-09T17:50:28Z)
• ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning [10.201633236997104]
  Large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities. We present ConceptPrune, wherein we first identify critical regions within pre-trained models responsible for generating undesirable concepts. Experiments across a range of concepts including artistic styles, nudity, object erasure, and gender debiasing demonstrate that target concepts can be efficiently erased by pruning a tiny fraction.
  arXiv  Detail & Related papers  (2024-05-29T16:19:37Z)
• Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models [57.86303579812877]
  Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Existing approaches often require numerous human interventions per image to achieve strong performances. We introduce a trainable concept realignment intervention module, which leverages concept relations to realign concept assignments post-intervention.
  arXiv  Detail & Related papers  (2024-05-02T17:59:01Z)
• Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting [51.606819347636076]
  We analyze concept-agnostic overfitting, which undermines non-customized concept knowledge, and concept-specific overfitting, which is confined to customize on limited modalities. We propose Infusion, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training modalities.
  arXiv  Detail & Related papers  (2024-04-22T09:16:25Z)
• Separable Multi-Concept Erasure from Diffusion Models [52.51972530398691]
  We propose a Separable Multi-concept Eraser (SepME) to eliminate unsafe concepts from large-scale diffusion models. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.
  arXiv  Detail & Related papers  (2024-02-03T11:10:57Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.