Search papers, labs, and topics across Lattice.
PRoADS, a novel audio steganography framework, leverages audio diffusion models to embed secret messages into the initial noise using orthogonal matrix projection. To combat reconstruction errors during diffusion inversion, the method incorporates Latent Optimization and Backward Euler Inversion, effectively minimizing latent reconstruction and diffusion inversion errors. Experiments show PRoADS achieves a BER of 0.15\% under 64 kbps MP3 compression, surpassing existing techniques and demonstrating robustness.
Achieve near-perfect audio steganography even under heavy MP3 compression by optimizing latent reconstruction and diffusion inversion errors.
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.
