# AWARE: Audio Watermarking with Adversarial Resistance to Edits

arXiv: https://arxiv.org/abs/2510.17512 · HTML: https://mlsanity.com/paper/2510.17512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Proactive Detection of Voice Cloning with Localized Watermarking](https://mlsanity.com/paper/2401.17264/) (2024)
- [CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition](https://mlsanity.com/paper/1801.08535/) (2018)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [Robust Audio Adversarial Example for a Physical Attack](https://mlsanity.com/paper/1810.11793/) (2018)
- [AudioMarkBench: Benchmarking Robustness of Audio Watermarking](https://mlsanity.com/paper/2406.06979/) (2024)
- [Security and Privacy in the Emerging Cyber-Physical World: A Survey](https://mlsanity.com/paper/2105.13347/) (2021)
- [Adversarial Shallow Watermarking](https://mlsanity.com/paper/2504.19529/) (2025)

## Abstract (arXiv)

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 through 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 systems.