为扩散模型生成图像防数据盗用，提出系统性防护方法
Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
- 基于对抗攻击设计保护扰动，防止未经授权的数据定制
- 构建完整评估框架，量化各类防护技术效果
- 适合关注模型版权与隐私安全的研究者参考
基于扩散的文生图模型在图像生成任务中展现出巨大潜力。然而，未经许可使用数据进行模型定制也带来了严重的隐私和知识产权问题。现有方法通过在定制样本上添加基于对抗攻击的保护扰动来应对。本文系统梳理了此类防护扰动方法，建立了威胁模型，分类了相关下游任务，并对技术设计进行了详细分析。同时，提出了一个完整的评估框架，旨在推动该领域的研究进展。
原文摘要 · Abstract (English)
Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual property issues. Existing methods introduce protective perturbations based on adversarial attacks, which are applied to the customization samples. In this systematization of knowledge, we present a comprehensive survey of protective perturbation methods designed to prevent unauthorized data usage in diffusion-based image generation. We establish the threat model and categorize the downstream tasks relevant to these methods, providing a detailed analysis of their designs. We also propose a completed evaluation framework for these perturbation techniques, aiming to advance research in this field.
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。