基于双域自然投影的低计算量水印移除
Low-Compute Watermark Removal via Dual-Domain Natural Projection
AI总结：
本文提出了一种轻量级且无需训练的攻击方法DAWN，通过在互补频率和语义空间中投影水印图像，以低计算成本实现高效的水印移除，同时保持结构和语义的完整性。
摘要：
有效的语义水印移除需要在三个竞争性目标之间取得平衡：高移除成功率、低感知失真和低计算成本。然而，现有的单图像攻击通常只优化前两个目标，实现强大的水印抑制，但依赖于昂贵的多步骤优化，限制了实际部署。在本文中，我们证明这种权衡是根本性的：目前没有任何方法能够同时实现这三个属性。我们引入DAWN，一种轻量级、无需训练的攻击方法，专门针对低计算成本的领域，同时保持竞争性的移除性能。DAWN通过将带水印的图像投影到自然图像先验上，在互补的频率和语义空间中压制偏离自然统计的水印信号，然后应用解耦的感知对齐步骤以最小化伪影来恢复视觉一致性。在多样化的像素、频率和潜在空间水印方案中，DAWN一致地降低了可检测性，同时保持结构和语义的保真度，证明了仅通过适度的感知退化即可实现高效的、低资源水印移除。我们的代码可在https://github.com/Pragati-Meshram/DAWN上获得。
英文摘要：
Effective removal of semantic watermarks requires balancing three competing objectives: \emph{high removal success}, \emph{low perceptual distortion}, and \emph{low computational cost}. However, existing single-image attacks typically optimize only for the first two, achieving strong watermark suppression but relying on expensive, multi-step optimization that limits practical deployment. In this work, we show that this trade-off is fundamental: no current approach achieves all three properties simultaneously. We introduce \textsc{DAWN}, a lightweight, training-free attack that explicitly targets the low-cost regime while maintaining competitive removal performance. \textsc{DAWN} works by projecting a watermarked image onto natural-image priors in complementary frequency and semantic spaces, suppressing watermark signals that deviate from natural statistics, and then applying a decoupled perceptual-alignment step to restore visual consistency with minimal artifact. Across diverse pixel-, frequency-, and latent-space watermarking schemes, \textsc{DAWN} consistently reduces detectability while preserving structural and semantic fidelity, demonstrating that efficient, low-resource watermark removal is feasible with only modest perceptual degradation. Our code is available at https://github.com/Pragati-Meshram/DAWN.
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。
