通过修改扩散模型的得分函数，实现高效隐写图像并保持模型性能。
Hiding Images in Diffusion Models by Editing Learned Score Functions
- 在反向扩散过程中特定步骤编辑得分函数嵌入图像。
- 提取图像质量高，模型行为与原版几乎无差别，速度提升数个数量级。
- 支持多接收方独立解密，适合实际通信场景。
利用神经网络进行数据隐写（即神经隐写术）已在判别型分类器和生成对抗网络中取得显著成果，但扩散模型中的隐写潜力仍待挖掘。现有方法因隐藏与提取过程与多个去噪步骤耦合，导致提取准确率、模型保真度和隐藏效率受限。为此，本文提出一种简单而有效的方法：在反向扩散过程中特定时间步编辑学习到的得分函数，以嵌入图像。此外，引入一种参数高效的微调方法，结合基于梯度的参数选择与低秩适应，提升模型保真度与隐藏效率。大量实验表明，该方法可提取人眼无法分辨的高质量图像，从样本到群体层面均能复现原始模型行为，且嵌入速度比以往方法快数个数量级。此外，该方法天然支持多接收方场景，通过独立解密通道实现。
原文摘要 · Abstract (English)
Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However, the potential of data hiding in diffusion models remains relatively unexplored. Current methods exhibit limitations in achieving high extraction accuracy, model fidelity, and hiding efficiency due primarily to the entanglement of the hiding and extraction processes with multiple denoising diffusion steps. To address these, we describe a simple yet effective approach that embeds images at specific timesteps in the reverse diffusion process by editing the learned score functions. Additionally, we introduce a parameter-efficient fine-tuning method that combines gradient-based parameter selection with low-rank adaptation to enhance model fidelity and hiding efficiency. Comprehensive experiments demonstrate that our method extracts high-quality images at human-indistinguishable levels, replicates the original model behaviors at both sample and population levels, and embeds images orders of magnitude faster than prior methods. Besides, our method naturally supports multi-recipient scenarios through independent extraction channels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。