IDEAW：具有可逆双嵌入的强大神经音频水印技术

IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding

September 29, 2024

作者: Pengcheng Li, Xulong Zhang, Jing Xiao, Jianzong Wang

cs.AI

摘要

音频水印技术将信息嵌入音频中，并能准确地从带水印的音频中提取信息。传统方法基于专家经验开发算法，将水印嵌入信号的时域或变换域中。随着深度神经网络的发展，基于深度学习的神经音频水印技术应运而生。与传统算法相比，神经音频水印技术通过在训练过程中考虑各种攻击方式，实现更好的鲁棒性。然而，目前的神经水印方法存在容量较低和感知性不佳的问题。此外，在神经音频水印技术中更为突出的水印定位问题尚未得到充分研究。本文设计了一种双嵌入水印模型以实现高效定位。我们还考虑攻击层对可逆神经网络在鲁棒性训练中的影响，改进模型以提高其合理性和稳定性。实验证明，所提出的IDEAW模型相较于现有方法，具有更高的容量和更高效的定位能力，能够抵御各种攻击。

English

The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of signals. With the development of deep neural networks, deep learning-based neural audio watermarking has emerged. Compared to traditional algorithms, neural audio watermarking achieves better robustness by considering various attacks during training. However, current neural watermarking methods suffer from low capacity and unsatisfactory imperceptibility. Additionally, the issue of watermark locating, which is extremely important and even more pronounced in neural audio watermarking, has not been adequately studied. In this paper, we design a dual-embedding watermarking model for efficient locating. We also consider the impact of the attack layer on the invertible neural network in robustness training, improving the model to enhance both its reasonableness and stability. Experiments show that the proposed model, IDEAW, can withstand various attacks with higher capacity and more efficient locating ability compared to existing methods.