The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures
This work identifies audio watermarking as a previously overlooked domain shift problem for securing speech-based applications, establishing the first benchmark for watermark-resilient anti-spoofing systems.
The study investigates how audio watermarking affects anti-spoofing systems, finding that it consistently degrades performance with higher watermark density leading to increased Equal Error Rates (EERs). To address this, the authors propose the Knowledge-Preserving Watermark Learning (KPWL) framework to adapt models while preserving detection capabilities.
This paper presents the first study on the impact of audio watermarking on spoofing countermeasures. While anti-spoofing systems are essential for securing speech-based applications, the influence of widely used audio watermarking, originally designed for copyright protection, remains largely unexplored. We construct watermark-augmented training and evaluation datasets, named the Watermark-Spoofing dataset, by applying diverse handcrafted and neural watermarking methods to existing anti-spoofing datasets. Experiments show that watermarking consistently degrades anti-spoofing performance, with higher watermark density correlating with higher Equal Error Rates (EERs). To mitigate this, we propose the Knowledge-Preserving Watermark Learning (KPWL) framework, enabling models to adapt to watermark-induced shifts while preserving their original-domain spoofing detection capability. These findings reveal audio watermarking as a previously overlooked domain shift and establish the first benchmark for developing watermark-resilient anti-spoofing systems. All related protocols are publicly available at https://github.com/Alphawarheads/Watermark_Spoofing.git