对比8种扩散模型防护方法，评估其在图像个性化中的隐私保护效果。
Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
- 测试8种基于扰动的防护方法在人脸与艺术作品上的表现。
- 在不同扰动预算下，评估视觉不可察觉性与防护有效性。
- 为实际应用提供防护方法选型参考，适合关注生成模型安全的研究者。
随着扩散模型在图像生成与个性化中的广泛应用，隐私泄露和内容滥用问题日益突出。本研究对八种基于扰动的防护方法——AdvDM、ASPL、FSGM、MetaCloak、Mist、PhotoGuard、SDS 和 SimAC——在人脸与艺术作品两个领域进行了全面比较。在不同扰动预算下，采用多种指标评估其视觉不可察觉性和防护效果。实验结果为防护方法的选择提供了实用指导。代码已公开：https://github.com/vkeilo/DiffAdvPerturbationBench。
原文摘要 · Abstract (English)
With the increasing adoption of diffusion models for image generation and personalization, concerns regarding privacy breaches and content misuse have become more pressing. In this study, we conduct a comprehensive comparison of eight perturbation based protection methods: AdvDM, ASPL, FSGM, MetaCloak, Mist, PhotoGuard, SDS, and SimAC--across both portrait and artwork domains. These methods are evaluated under varying perturbation budgets, using a range of metrics to assess visual imperceptibility and protective efficacy. Our results offer practical guidance for method selection. Code is available at: https://github.com/vkeilo/DiffAdvPerturbationBench.
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。