Watermarking generative content serves as a vital tool for authentication, ownership protection, and mitigation of potential misuse. Existing watermarking methods face the challenge of balancing robustness and concealment. They empirically inject a watermark that is both invisible and robust and passively achieve concealment by limiting the strength of the watermark, thus reducing the robustness. In this paper, we propose to explicitly introduce a watermark hiding process to actively achieve concealment, thus allowing the embedding of stronger watermarks. To be specific, we implant a robust watermark in an intermediate diffusion state and then guide the model to hide the watermark in the final generated image. We employ an adversarial optimization algorithm to produce the optimal hiding prompt guiding signal for each watermark. The prompt embedding is optimized to minimize artifacts in the generated image, while the watermark is optimized to achieve maximum strength. The watermark can be verified by reversing the generation process. Experiments on various diffusion models demonstrate the watermark remains verifiable even under significant image tampering and shows superior invisibility compared to other state-of-the-art robust watermarking methods.

翻译：生成式内容水印技术作为认证、所有权保护及潜在滥用防范的关键工具，其现有方法面临鲁棒性与隐蔽性难以兼顾的挑战。现有方法通常通过经验性注入水印来实现隐形与鲁棒性，并以限制水印强度的被动方式达成隐蔽效果，这往往导致鲁棒性降低。本文提出显式引入水印隐藏过程以主动实现隐蔽性，从而允许嵌入更强水印。具体而言，我们在扩散过程的中间状态植入鲁棒水印，随后引导模型将水印隐藏于最终生成图像中。我们采用对抗优化算法为每个水印生成最优的隐藏提示引导信号：通过优化提示嵌入最小化生成图像中的伪影，同时优化水印以实现最大强度。该水印可通过逆转生成过程进行验证。在不同扩散模型上的实验表明，即使图像遭受显著篡改，水印仍可被有效验证，且相较于其他先进鲁棒水印方法展现出更优的不可感知性。