個性化擴散模型對抗模仿的幾乎零成本保護

摘要

最近擴散模型的進步革新了影像生成，但也帶來了濫用的風險，例如複製藝術品或生成深偽。現有的影像保護方法雖然有效，卻難以平衡保護效能、隱形性和延遲，因此限制了實際應用。我們引入了擾動預訓練以降低延遲，並提出了一種混合擾動方法，動態適應輸入影像以最小化性能降低。我們的新型訓練策略在多個 VAE 特徵空間中計算保護損失，而推斷時的自適應目標保護增強了魯棒性和隱形性。實驗顯示出具有改善隱形性和大幅減少推斷時間的相當保護性能。代碼和演示可在https://webtoon.github.io/impasto找到。

English

Recent advancements in diffusion models revolutionize image generation but pose risks of misuse, such as replicating artworks or generating deepfakes. Existing image protection methods, though effective, struggle to balance protection efficacy, invisibility, and latency, thus limiting practical use. We introduce perturbation pre-training to reduce latency and propose a mixture-of-perturbations approach that dynamically adapts to input images to minimize performance degradation. Our novel training strategy computes protection loss across multiple VAE feature spaces, while adaptive targeted protection at inference enhances robustness and invisibility. Experiments show comparable protection performance with improved invisibility and drastically reduced inference time. The code and demo are available at https://webtoon.github.io/impasto

個性化擴散模型對抗模仿的幾乎零成本保護

Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models

摘要

Summary

Support