Back to Paper
cs.CVcs.CR
Local ID: 2603.29742v2
AI Summary: gemma4:e4b
SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark
By Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang
Revision History Timeline
v13/31/2026
3/31/2026
No submitter comment provided.
v24/1/2026
4/1/2026
No submitter comment provided.
★ Version indexed in ExplorerComparing v1 vs v2
Green = Added • Red = Removed
Title Comparison
SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark
Authors Comparison
No author changes.
v1 Comment
No comment for this version.
v2 Comment
No comment for this version.
Abstract Word Diff
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.