Recently, deep learning has been gradually applied to digital watermarking, which avoids the trouble of hand-designing robust transforms in traditional algorithms. However, most of the existing deep watermarking algorithms use encoder–decoder architecture, which is redundant. This paper proposes a novel audio watermarking algorithm based on adversarial perturbation, AAW. It adds tiny, imperceptible perturbations to the host audio and extracts the watermark with a pre-trained decoder. Moreover, the AAW algorithm also uses an attack simulation layer and a whitening layer to improve performance. The AAW algorithm contains only a differentiable decoder, so it reduces the redundancy. The experimental results also demonstrate that the proposed algorithm is effective and performs better than existing audio watermarking algorithms.

Digital audio watermarking is a promising technology for copyright protection, yet its low embedding capacity remains a challenge for widespread applications. In this paper, the spread-spectrum watermarking algorithm is viewed as a communication channel, and the embedding capacity is analyzed and modeled with information theory. Following this embedding capacity model, we propose the extended-codebook spread-spectrum (ECSS) watermarking algorithm to heighten the embedding capacity. In addition, the diversity reception (DR) mechanism is adopted to optimize the proposed algorithm to obtain both high embedding capacity and strong robustness while the imperceptibility is guaranteed. We experimentally verify the effectiveness of the ECSS algorithm and the DR mechanism, evaluate the performance of the proposed algorithm against common signal processing attacks, and compare the performance with existing high-capacity algorithms. The experiments demonstrate that the proposed algorithm achieves a high embedding capacity with applicable imperceptibility and robustness.

Audio watermarking is a promising technique for copyright protection of audio data. The existing audio watermarking algorithms cannot satisfy requirements on imperceptibility, embedding capacity, and robustness, especially against desynchronization attacks, such as cropping, jittering, and time-scale modification. This paper proposes a novel audio watermarking algorithm based on local invariant points and adaptive embedding strength (LIPAS). We consider one feature robust to desynchronization attacks, i.e., local invariant points, and use these invariant points as positional references for the embedding regions. An adaptive embedding strength strategy is proposed to enhance the imperceptibility of the watermark and ensure robustness. The watermarks are embedded into the audio vectors using a polarity adjustment method. The effectiveness, imperceptibility, and robustness of the LIPAS algorithm were demonstrated in the experiments.