|国家预印本平台
首页|Accurate Latent Inversion for Generative Image Steganography via Rectified Flow

Accurate Latent Inversion for Generative Image Steganography via Rectified Flow

Accurate Latent Inversion for Generative Image Steganography via Rectified Flow

来源:Arxiv_logoArxiv
英文摘要

Steganography based on diffusion models has attracted increasing attention due to its ability to generate high-quality images and exhibit strong robustness. In such approaches, the secret message is first embedded into the initial latent variable, and then the stego image is generated through the forward process. To extract the message, an inversion process is required to reconstruct the latent variables from the received image. However, inaccurate latent inversion leads to significant discrepancies between the reconstructed and original latent variables, rendering message extraction infeasible. To address this issue, we propose \textbf{RF-Stego}, a novel generative image steganography method that enables accurate latent inversion and significantly improves extraction accuracy. First, we develop the \textbf{P}ath \textbf{C}onsistency \textbf{L}inear \textbf{I}nversion (\textbf{PCLI}), which imposes formal constraints on the inversion process. By explicitly aligning it with the forward generation path and modeling both directions along a shared linear path, PCLI eliminates path mismatch and ensures path consistency throughout the steganographic process. Second, through rigorous theoretical proof, we demonstrate that \textbf{R}ectified \textbf{F}low \textbf{(RF)} offers both theoretical reversibility and numerical stability in the inversion process. Based on this, we replace traditional unstable samplers with RF sampler which effectively improves the numerical precision of the inversion process. Experimental results show RF-Stego outperforms state-of-the-art methods in terms of extraction accuracy, image quality, robustness, security and generation efficiency.

Yuqi Qian、Yun Cao、Meiyang Lv、Haocheng Fu

计算技术、计算机技术

Yuqi Qian,Yun Cao,Meiyang Lv,Haocheng Fu.Accurate Latent Inversion for Generative Image Steganography via Rectified Flow[EB/OL].(2025-08-01)[2025-08-11].https://arxiv.org/abs/2508.00434.点此复制

评论