Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
This work addresses privacy and content misuse concerns in diffusion model personalization, offering a comprehensive evaluation for practitioners, but it is incremental as it focuses on comparing existing methods.
The study compared eight perturbation-based protection methods for diffusion model personalization across portrait and artwork domains, evaluating them under different perturbation budgets to provide practical guidance for method selection.
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.