# XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

arXiv: https://arxiv.org/abs/2502.04230 · HTML: https://mlsanity.com/paper/2502.04230/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 75 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [FMA: A Dataset For Music Analysis](https://mlsanity.com/paper/1612.01840/) (2016)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [Proactive Detection of Voice Cloning with Localized Watermarking](https://mlsanity.com/paper/2401.17264/) (2024)
- [Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion](https://mlsanity.com/paper/2402.10009/) (2024)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning](https://mlsanity.com/paper/2311.13127/) (2023)
- [Detecting Voice Cloning Attacks via Timbre Watermarking](https://mlsanity.com/paper/2312.03410/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise](https://mlsanity.com/paper/2311.13091/) (2023)
- [CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code](https://mlsanity.com/paper/2404.15639/) (2024)
- [AudioMarkBench: Benchmarking Robustness of Audio Watermarking](https://mlsanity.com/paper/2406.06979/) (2024)
- [Deepfakes, Misinformation, and Disinformation in the Era of Frontier AI, Generative AI, and Large AI Models](https://mlsanity.com/paper/2311.17394/) (2023)
- [Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model](https://mlsanity.com/paper/2401.14542/) (2024)
- ["Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World](https://mlsanity.com/paper/2109.09598/) (2021)
- [Between Copyright and Computer Science: The Law and Ethics of Generative AI](https://mlsanity.com/paper/2403.14653/) (2024)

## Built on by (most cited first, 5 of 5)

- [Self Voice Conversion as an Attack against Neural Audio Watermarking](https://mlsanity.com/paper/2601.20432/) (2026)
- [Latent-Mark: An Audio Watermark Robust to Neural Codec Compression](https://mlsanity.com/paper/2603.05310/) (2026)
- [MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech](https://mlsanity.com/paper/2605.01515/) (2026)
- [Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation](https://mlsanity.com/paper/2512.06304/) (2025)
- [GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability](https://mlsanity.com/paper/2610.15082/) (2026)

## Abstract (arXiv)

The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data provenance, and the spread of misinformation via deepfake audio. Watermarking offers a proactive solution by embedding imperceptible yet identifiable and traceable signals into audio content. While recent neural network-based watermarking methods like WavMark and AudioSeal have improved robustness and quality, they struggle to jointly optimize both robust detection and accurate attribution. This paper introduces Cross-Attention Robust Audio Watermark (XATTNMARK), which bridges this gap by leveraging partial parameter sharing between the generator and the detector, a cross-attention mechanism for efficient message retrieval, and a temporal conditioning module for improved message distribution. Additionally, we propose a psychoacoustic-aligned time-frequency (TF) masking loss that captures fine-grained auditory masking effects, improving watermark imperceptibility. XATTNMARK achieves state-of-the-art performance in both detection and attribution, demonstrating superior robustness against a wide range of audio transformations, including challenging generative editing at varying strengths. This work advances audio watermarking for protecting intellectual property and ensuring authenticity in the era of generative AI.