AI & ML
Fast and Strong Image Protection against Diffusion Personalization
arXiv cs.CR0 views
arXiv:2611.22494v1 Announce Type: cross Abstract: Personalized text-to-image diffusion models can reproduce a person from a handful of photographs. Image protection perturbs each image before publication so that fine-tuning on it fails, but it optimizes every perturbation from scratch, so its cost grows with the number of images. We present the protective diffusion model (PDM), which is trained once and samples the perturbation of a new image over many denoising steps. PDM distills an iterative teacher and is then post-trained with the target residual projection (TRP) loss as a reward, a stronger objective than existing ones. PDM outperforms nine baselines on faces and artworks and nearly matches its teacher at a tenth of the cost.
Source:https://arxiv.org/abs/2611.22494PreviousA Little Advice Suffices: Diffie-Hellman Is as Hard as Discrete LogarithmNextMissing Security-Fix Backporting for GitHub Actions Workflows
Related posts
Daily Dose of DevOps — Log pipeline: across multiple cloud platforms
0dev.to
Why browser agents waste tokens, and how to stop it
0dev.to
State of HTML 2026: built-in elements win, form controls still hurt
0dev.to
Making a portfolio of open public-sector projects that keeps itself honest
0dev.to
Keeping AI answers findable when you use ChatGPT, Claude and Gemini
0dev.to
What is the Model Context Protocol (MCP)? Tools, resources, transports and auth, explained by someone who built a server
0dev.to