通过编辑已学习的得分函数在扩散模型中隐藏图像
Hiding Images in Diffusion Models by Editing Learned Score Functions
AI总结：
针对现有扩散模型数据隐藏方法精度、保真度与效率不足的问题，提出通过编辑得分函数在特定时间步嵌入图像，并结合梯度参数选择与LoRA的参数高效微调法，实现了高提取质量、模型行为复现与更快嵌入，还支持多接收方场景。
摘要：
利用神经网络隐藏数据（即神经隐写术）已在判别式分类器和生成对抗网络中均取得了显著成效。然而，扩散模型中的数据隐藏潜力仍相对未被充分探索。现有方法在实现高提取精度、模型保真度和隐藏效率方面存在局限，这主要源于隐藏与提取过程和多步去噪扩散步骤相互纠缠。为解决这些问题，我们提出了一种简单却有效的方法：通过编辑已学习的得分函数，在反向扩散过程的特定时间步嵌入图像。此外，我们引入了一种参数高效的微调方法，该方法结合了基于梯度的参数选择与低秩适配（LoRA），以提升模型保真度和隐藏效率。综合实验表明，我们的方法能提取出人类无法区分真伪的高质量图像，在样本层面和群体层面均能复现原始模型的行为，且嵌入图像的速度比现有方法快数个数量级。此外，该方法通过独立的提取通道天然支持多接收方场景。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
