AWARE: Audio Watermarking with Adversarial Resistance to Edits

Prevailing practice in learning-based audio watermarking is to pursue robustness by expanding the set of simulated distortions during training. However, such surrogates are narrow and prone to overfitting. This paper presents AWARE (Audio Watermarking with Adversarial Resistance to Edits), an alternative approach that avoids reliance on attack-simulation stacks and handcrafted differentiable distortions. Embedding is obtained via adversarial optimization in the time-frequency domain under a level-proportional perceptual budget. Detection employs a time-order-agnostic detector with a Bitwise Readout Head (BRH) that aggregates temporal evidence into one score per watermark bit, enabling reliable watermark decoding even under desynchronization and temporal cuts. Empirically, AWARE attains high audio quality and speech intelligibility (PESQ/STOI) and consistently low BER across various audio edits, often surpassing representative state-of-the-art learning-based audio watermarking systems.

Key Contributions

• Adversarial watermark embedding in the time-frequency domain under a level-proportional perceptual budget, avoiding reliance on handcrafted differentiable distortion surrogates
• Time-order-agnostic detector with a Bitwise Readout Head (BRH) that aggregates temporal evidence per bit, enabling robust decoding under desynchronization and temporal cuts
• Empirical demonstration of consistently low BER across diverse audio edits while maintaining high PESQ/STOI quality scores, surpassing state-of-the-art audio watermarking baselines

🛡️ Threat Analysis

Details

Similar Papers