Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumption: verification can succeed only if the diffusion trajectory can be faithfully reconstructed. This reliance on trajectory recovery constitutes a fundamental and exploitable vulnerability. We propose $\underline{\mathbf{S}}$tochastic $\underline{\mathbf{Hi}}$dden-Trajectory De$\underline{\mathbf{f}}$lec$\underline{\mathbf{t}}$ion ($\mathbf{SHIFT}$), a training-free attack that exploits this common weakness across diverse watermarking paradigms. SHIFT leverages stochastic diffusion resampling to deflect the generative trajectory in latent space, making the reconstructed image statistically decoupled from the original watermark-embedded trajectory while preserving strong visual quality and semantic consistency. Extensive experiments on nine representative watermarking methods spanning noise-space, frequency-domain, and optimization-based paradigms show that SHIFT achieves 95%--100% attack success rates with nearly no loss in semantic quality, without requiring any watermark-specific knowledge or model retraining.

翻译：基于扩散的水印方法通过操控初始噪声或逆扩散轨迹来嵌入可验证标记。然而，这些方法共享一个关键假设：只有当扩散轨迹能够被忠实重构时，验证才能成功。这种对轨迹恢复的依赖构成了一种根本性的、可被利用的漏洞。我们提出**随机隐藏轨迹偏转**（SHIFT），这是一种无需训练的攻破方法，能够利用不同水印范式中的这一共同弱点。SHIFT利用随机扩散重采样在潜在空间中偏转生成轨迹，使得重构图像在统计上与原始嵌入水印的轨迹解耦，同时保持强大的视觉质量和语义一致性。在涵盖噪声空间、频域和基于优化的九种代表性水印方法上的大量实验表明，SHIFT在几乎不损失语义质量的情况下实现了95%--100%的攻破成功率，且无需任何水印特定知识或模型重训练。