UniDef：抵御未授权图像篡改的通用防御
UniDef: Universal Defense Against Unauthorized Image Manipulation
把「保护图像不被扩散编辑」从逐步局部扰动升级为全局去噪方向扰动，并用有限差分雅可比估计替代模型相关梯度，做视觉研究者可将其作为模型无关对抗扰动的通用构造手段，用于跨模型、跨编辑任务的保护与红队评估。
原文依据 we devise a Finite Difference-based Jacobian Estimation module to approximate the global gradient in a model-agnostic manner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论针对未授权扩散编辑的图像保护已取得令人鼓舞的进展。然而，现有方法存在两个关键局限：（1）它们仅在局部步骤上扰动去噪方向，导致生成图像仍保留原始或编辑后的语义；（2）其优化严重依赖特定模型的梯度，限制了跨不同模型与任务的可迁移保护能力。为应对这些挑战，我们提出通用防御（UniDef）框架，用于抵御未授权图像篡改。具体而言，我们首先发现不同变体的扩散模型在完整去噪过程中往往追求一致的分布目标。基于这一发现，我们设计了分布一致性偏移策略，在全局去噪过程中扰动扩散方向，从而破坏整体图像语义。此外，为缓解模型依赖问题，我们设计了基于有限差分的雅可比估计模块，以模型无关的方式近似全局梯度，从而确保更具可迁移性的保护。得益于上述设计，我们的方法生成的图像不再保留图像语义，同时具备优异的泛化能力。大量实验表明，UniDef 不仅优于现有方法，而且在多种模型与任务上展现出通用保护能力。
英文原文摘要 1430 字符
Image protection against unauthorized diffusion-based editing has achieved encouraging progress. However, existing methods face two critical limitations: (1) They only disturb the denoising direction at local step, resulting in generated images still retaining original or edited semantics. (2) Their optimization rely heavily on model-specific gradient, limiting transferable protection across different models and tasks. To address these challenges, we propose a Universal Defense (UniDef) framework for protection against unauthorized image manipulation. Specifically, we first discover that different variants of diffusion models tend to pursue a consistent distribution objective during complete denoising process. Based on this discovery, we design Consistent Distribution Deviation strategy to perturb the diffusion direction at the global denoising, thereby disrupting the overall image semantics. Furthermore, to mitigate model dependency, we devise a Finite Difference-based Jacobian Estimation module to approximate the global gradient in a model-agnostic manner, thus ensuring more transferable protection. Benefiting from the above designs, our method yields generated images no longer preserve the image semantic while possessing excellent generalization. Extensive experiments demonstrate that our UniDef not only outperforms existing methods, but also exhibits universal protection across diverse models and tasks.