用少量敏感数据训练，防止扩散模型生成敏感内容。
Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
- 仅用未标注数据和少量敏感数据，构建正-未标记扩散模型
- 在无正常数据标签情况下仍能有效降低敏感数据生成概率
- 适合需隐私保护的图像生成场景，如医疗或金融
扩散模型虽强大，但常生成用户不希望的敏感数据，主要因大规模未标注训练数据中混有敏感内容。由于完全标注这些数据不现实，本文提出正-未标记扩散模型，仅利用少量已标注敏感数据与大量未标注数据，即可近似正常数据的证据下界（ELBO）。该方法无需正常数据标签，即可最大化正常数据的ELBO并最小化敏感数据的ELBO，从而确保仅生成正常数据。在多种数据集和设置下的实验表明，该方法可有效防止敏感图像生成，且不影响图像质量。
原文摘要 · Abstract (English)
Diffusion models are powerful generative models but often generate sensitive data that are unwanted by users, mainly because the unlabeled training data frequently contain such sensitive data. Since labeling all sensitive data in the large-scale unlabeled training data is impractical, we address this problem by using a small amount of labeled sensitive data. In this paper, we propose positive-unlabeled diffusion models, which prevent the generation of sensitive data using unlabeled and sensitive data. Our approach can approximate the evidence lower bound (ELBO) for normal (negative) data using only unlabeled and sensitive (positive) data. Therefore, even without labeled normal data, we can maximize the ELBO for normal data and minimize it for labeled sensitive data, ensuring the generation of only normal data. Through experiments across various datasets and settings, we demonstrated that our approach can prevent the generation of sensitive images without compromising image quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。