LiBRA：通过双向潜在优化的检测感知图像水印移除

中文摘要 AI 辅助

数字水印支持AI生成图像的来源归属，但其可靠性取决于对移除攻击的抵抗能力。一些攻击试图通过强制解码出的水印与原始水印不同来移除水印。然而，这可能会产生一个倒置但仍可检测的水印，导致移除失败，而进一步改变水印的尝试可能会不必要地降低图像质量。为解决这些局限性，我们提出了LiBRA（潜在带内双向移除攻击），其目标是使水印不可检测，同时保持图像质量。LiBRA不是持续推动水印走向倒置，而是调整图像以隐藏水印，而不鼓励可能降低图像质量的进一步改变。一些攻击持续将解码位推离原始水印，即使进一步改变会保持可检测性并损害图像质量。在能够访问水印密钥和解码器的情况下，LiBRA在公共自编码器的潜在空间中做出有界改变。与无法纠正过度倒置的倒置驱动目标不同，LiBRA从任一方向引导平均解码置信度趋向随机猜测。这有助于避免出现倒置但可检测的水印。保持各个位灵活允许图像质量约束偏向于损害较小的改变，而可选的频率引导掩码限制了它们的位置。我们使用精确的双侧二项检验来验证移除效果，而不是假设置信度目标保证成功。

英文摘要

Digital watermarking supports source attribution for AI-generated images, but its reliability depends on resistance to removal attacks. Some attacks attempt to remove watermarks by forcing the decoded watermark to differ from the original. However, this can produce an inverted watermark that remains detectable, causing removal to fail, while further attempts to alter the watermark may unnecessarily degrade image quality. To address these limitations, we present LiBRA (Latent In-band Bidirectional Removal Attack), which aims to make watermarks undetectable while preserving image quality. Instead of continually pushing the watermark toward inversion, LiBRA adjusts the image to conceal the watermark without encouraging further changes that could degrade image quality. Some attacks keep pushing decoded bits away from the original watermark, even when further changes preserve detectability and damage image quality. With access to the watermark key and decoder, LiBRA makes bounded changes in a public autoencoder's latent space. Unlike inversion-driven objectives that cannot correct excessive inversion, LiBRA guides average decoding confidence toward random guessing from either direction. This helps avoid an inverted but detectable watermark. Leaving individual bits flexible allows image-quality constraints to favor less damaging changes, while an optional frequency-guided mask limits their location. We verify removal using an exact two-sided binomial test rather than assuming the confidence target guarantees success.

发表机构

• City University of Macau（澳门城市大学）
• Xi’an Jiaotong University（西安交通大学）
• University of Electronic Science and Technology of China（电子科技大学）
• Xidian University（西安电子科技大学）

机构由 AI 辅助整理，请以论文原文为准。