用扩散模型隐写音频，抗压缩能力强，误码率仅0.15%
PRoADS: Provably Secure and Robust Audio Diffusion Steganography with latent optimization and backward Euler Inversion
- 通过正交矩阵投影将秘密信息嵌入扩散模型初始噪声
- 在64kbps MP3压缩下误码率低至0.15%
- 结合潜在优化与反向欧拉反演，提升解码鲁棒性
本文提出PRoADS，一种基于音频扩散模型的可证明安全且鲁棒的隐写框架。作为生成式隐写方案，PRoADS通过正交矩阵投影将秘密消息嵌入扩散模型的初始噪声中。为解决扩散反演中的重建误差导致高误码率的问题，引入潜在优化与反向欧拉反演，以最小化潜在空间重建误差和扩散反演误差。大量实验表明，该方案在64 kbps MP3压缩下仍保持极低的误码率（0.15%），显著优于现有方法，展现出强大鲁棒性。
原文摘要 · Abstract (English)
This paper proposes PRoADS, a provably secure and robust audio steganographic framework based on audio diffusion models. As a generative steganography scheme, PRoADS embeds secret messages into the initial noise of diffusion models via orthogonal matrix projection. To address the reconstruction errors in diffusion inversion that cause high bit error rates (BER), we introduce Latent Optimization and Backward Euler Inversion to minimize the latent reconstruction and diffusion inversion errors. Comprehensive experiments demonstrate that our scheme sustains a remarkably low BER of 0.15\% under 64 kbps MP3 compression, significantly outperforming existing methods and exhibiting strong robustness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。