评估扩散个性化中的对抗性保护:一项综合研究
Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
AI总结:
本文系统比较了八种基于扰动的扩散个性化保护方法,在肖像与艺术作品场景下评估其不可感知性和保护效果,为方法选择提供实用指导。
摘要:
随着扩散模型在图像生成和个性化中的日益普及,关于隐私泄露和内容滥用的担忧变得更加紧迫。在本研究中,我们对八种基于扰动的保护方法进行了全面比较:AdvDM、ASPL、FSGM、MetaCloak、Mist、PhotoGuard、SDS 和 SimAC,涵盖肖像和艺术作品两个领域。这些方法在不同的扰动预算下进行评估,使用一系列指标来评估视觉不可感知性和保护效果。我们的结果为方法选择提供了实用指导。代码可在以下地址获取:https://github.com/vkeilo/DiffAdvPerturbationBench。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。