SyncGuard: Robust Audio Watermarking Capable of Countering Desynchronization Attacks

TL;DR

SyncGuard is a novel learning-based audio watermarking scheme that robustly resists desynchronization attacks by embedding watermarks in a time-independent manner and utilizing advanced neural network features.

Contribution

The paper introduces SyncGuard, a new audio watermarking method that employs frame-wise embedding and multi-resolution feature extraction to improve robustness and eliminate localization.

Findings

Outperforms existing methods in robustness against attacks

Effectively handles variable-length audio segments

Maintains high auditory quality

Abstract

Audio watermarking has been widely applied in copyright protection and source tracing. However, due to the inherent characteristics of audio signals, watermark localization and resistance to desynchronization attacks remain significant challenges. In this paper, we propose a learning-based scheme named SyncGuard to address these challenges. Specifically, we design a frame-wise broadcast embedding strategy to embed the watermark in arbitrary-length audio, enhancing time-independence and eliminating the need for localization during watermark extraction. To further enhance robustness, we introduce a meticulously designed distortion layer. Additionally, we employ dilated residual blocks in conjunction with dilated gated blocks to effectively capture multi-resolution time-frequency features. Extensive experimental results show that SyncGuard efficiently handles variable-length audio segments, outperforms state-of-the-art methods in robustness against various attacks, and delivers superior auditory quality.