Audio Watermarking

Follow this topic Ask about this topic

Audio watermarking studies how to attach hidden or audible-to-machines information to speech, music, and synthesized audio so its source or integrity can later be checked. Methods range from post-hoc signal and spectrogram perturbations to marks embedded in neural-codec latents, semantic or token representations, and generation-time TTS or music models. Researchers test detection and payload recovery under compression, denoising, resynthesis, source separation, and other edits, with benchmarks increasingly measuring false positives and distribution shifts. The central tension is making marks survive powerful transformations and removal attacks without harming sound quality, while ensuring provenance marks do not mislead or weaken deepfake detectors.

Latest papers

32 papers2 papers in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

Averaging Collusion Breaks Traceability in Personalized Neural Audio Watermarking
Nov 3, 2026Yangming Liu, Haiyun Li, Dongfu Song +4Audio Watermarking Robust Watermarking
Tsinghua University, Shenzhen, China
ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking
Nov 3, 2026Binhao Ma, Weikang Ding, Hanqing Guo +5Audio Watermarking Black-Box Adversarial Attacks
University of Missouri–Kansas City · Indiana University Bloomington · University of South Florida +1
Backward Compatibility in Zero-Bit Neural Audio Watermarking
Oct 15, 2026Admir Krnić, Kosta Pavlović, Petar Nedić +3Audio Watermarking Robust Watermarking
DeepMark
GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability
Oct 10, 2026Yihang Zhang, Weicai Yan, Qifei Zhang +2Audio Watermarking Robust Watermarking
Zhejiang University
NeuMark-Native: Robust Text-to-Speech-Native Watermarking Through Full Utilization of Neural Audio Codec Latent Space
Oct 4, 2026Annan Wu, Wen-Chin Huang, Tomoki TodaAudio Watermarking Robust Watermarking
Nagoya University, Japan
Learning to Watermark Speech Synthesis Against Model-Driven Reconstruction
Oct 3, 2026Weizhi Liu, Yue Li, Hui Tian +1Audio Watermarking Robust Watermarking
East China Normal University, Shanghai, China · Huaqiao University, Xiamen, China
Watermarks and Fingerprints as Soft Bindings for Content Provenance: An Open-Licence Benchmark for Images, Audio and Video
Oct 2, 2026Seyedmahdi Kazempourradi, Ramtin Mojtahedi, Behrang MohseniData Provenance Robust Watermarking
Original Pictures Technologies, Inc., Delaware, USA
Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech
Sep 27, 2026Kanghwi Lee, Kyeongseok Jeong, Jeongmin LiuAudio Watermarking Robust Watermarking
Institute of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland · NAVER Cloud
No Time to Collapse: Unlocking Robustness and Multiplexed Capacity in Frozen Audio Watermarkers
Sep 24, 2026Xuanye Wang, Linxi Li, Yechen Wang +3Audio Watermarking Robust Watermarking
OfSpectrum, Inc., Los Angeles, CA, USA · University of Warwick, Coventry, United Kingdom
The Vulnerability of Neural Audio Watermarks under Speech Enhancement
Sep 24, 2026Xincong Zhong, Shengyao Wang, Lingfeng Yao +4Watermark Removal Audio Watermarking
Waseda University, Japan · University of Houston, USA
Latent Audio Watermarking for Robustness to Neural Codec Resynthesis
Sep 22, 2026Lovro Brulec, Sahil Karawade, Leonard KinzingerAudio Watermarking Robust Watermarking
Munich Music Labs · Technical University of Munich
NeuMark: Neural Codec Resynthesis-Robust Audio Watermarking in the Codec Latent Space
Sep 22, 2026Annan Wu, Wen-Chin Huang, Tomoki TodaAudio Watermarking Robust Watermarking
Nagoya University, Japan
CRAW: Codec Robust Audio Watermarking
Sep 2, 2026David Chernin, Ethan FetayaAudio Watermarking Robust Watermarking
Bar-Ilan University, Ramat Gan, Israel · NVIDIA
Combining Self-Embedding Audio Watermarking with Ultra-Low-Bitrate Neural Codecs
Aug 26, 2026Yigitcan Özer, Xin Wang, Zhe Zhang +1Audio Watermarking Audio Deepfake Detection
National Institute of Informatics, Tokyo, Japan
On the Robustness of Audio Deepfake Detection under Audio Watermarking
Aug 25, 2026Zi Qian Yong, Ajinkya Kulkarni, Julia Lau +4Audio Deepfake Detection Robustness Audio Deepfake Detection
School of Information Technology, Monash University, Malaysia campus · Idiap Research Institute, Switzerland
AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS
Aug 23, 2026Timothy Tin-Long, Jian Zhu, Aidan Pine +1Audio Watermarking Robust Watermarking
National Research Council Canada, Canada · University of British Columbia, Canada
How Fragile Is Your Watermark? Training-Free Structural Removal of Neural Audio Watermarks
Aug 17, 2026Likhith KumaraWatermark Removal Audio Watermarking
Indian Institute of Technology Madras, Chennai, India
Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness
Jul 23, 2026Zi Hu, Houmin Sun, Linxi Li +4Audio Watermarking Neural Audio Codecs
Digital Innovation Research Center, Duke Kunshan University, Kunshan, China · OfSpectrum, Inc., Los Angeles, USA · University of Warwick, Coventry, United Kingdom +1
SSTMark: Robust Training-Free Semantic-Level Speech Watermarking
Jul 20, 2026Kuan-Lin Chu, Jun-Cheng Chen, Chun-Shien LuAudio Watermarking Robust Watermarking
CITI, Academia Sinica · Taiwan, ROC · IIS, Academia Sinica
MusicMark: A Robust Generative Watermarking Framework for Music Generation
Jul 13, 2026Seohwan Yun, Jeeyoung Yun, Yongjin Kim +2Audio Watermarking Robust Watermarking
Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea · Department of Computer Engineering, Inha University, Incheon, Republic of Korea
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
Jun 22, 2026Nicolas M. Müller, Pascal DebusAudio Watermarking Audio Deepfake Detection
Fraunhofer AISEC, Germany · Resemble AI
Learning to Evade: Adaptive Attacks on Audio Watermarking
Jun 21, 2026Weikang Ding, Hanqing Guo, Rui Duan +4Watermark Removal Audio Watermarking
University of Missouri-Kansas City, USA · University of Hawaii at Manoa, USA · University of South Florida, USA +2
LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity
Jun 19, 2026Kexin Li, Xiao Hu, Ilya Grishchenko +1Audio Watermarking Robust Watermarking
University of Toronto, Canada
DuraMark: Duration-Embedded Watermarking in LLM-based TTS
Jun 13, 2026Zhenwei Mou, Weili Jiang, Liping Chen +4Audio Watermarking TTS Synthesis
University of Science and Technology of China, China · Institute of Forensic Science, Ministry of Public Security, China · The Hong Kong Polytechnic University, China
VoxWatermark: A Large-Scale Benchmark for Audio Watermark Detection under Perturbations
Jun 13, 2026Farnaz Sedaghati, Yuxi Wang, Zicheng Weng +1Audio Watermarking Robust Watermarking
University of Tehran, Iran · Nanyang Technological University, Singapore
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
Jun 10, 2026Haiyun Li, Shuhai Peng, Zhisheng Zhang +4Audio Watermarking Robust Watermarking
Shenzhen International Graduate School, Tsinghua University, China · Pengcheng Laboratory, China · Independent Researcher, China
Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
May 28, 2026Lingfeng Yao, Xincong Zhong, Chenpei Huang +6Watermark Removal Audio Watermarking
University of Houston · Waseda University · UC Berkeley +3
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
May 25, 2026Georgios Milis, Yubin Qin, Yihan Wu +1Audio Watermarking Robust Watermarking
Department of Computer Science, University of Maryland, College Park, USA.
MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
May 2, 2026Yutong Jin, Qi Li, Lingshuang Liu +1Audio Watermarking Robust Watermarking
Department of Electrical and Computer Engineering, Queen’s University, Kingston, ON, Canada · Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada
LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization
Apr 27, 2026Bokang Zeng, Zheng Gao, Xiaoyu Li +2Audio Watermarking Deepfake Detection
School of Computer Science and Engineering UNSW Sydney Sydney, Australia · School of Information and Communication Technology Griffith University Brisbane, Australia

Nov 3, 2026J/K move · Enter open · S save

Averaging Collusion Breaks Traceability in Personalized Neural Audio Watermarking

Yangming Liu, Haiyun Li, Dongfu Song, Ziang Xu+3

Tsinghua University, Shenzhen, China

Audio Watermarking Robust Watermarking

Open paper AskPDF arXiv

Personalized neural audio watermarking systems embed user-specific payloads into audio to trace the user associated with a leaked or misused copy. Existing evaluations mainly assume access to a single personalized copy, but real-world distribution may expose multiple copies of the same recording. We find that simple sample-wise averaging breaks traceability: averaging only two copies produces tracing-failure rates of 87.7-99.7% across the five systems while largely preserving audio quality. Decoder outputs show distinct responses to coalition payload composition across systems, with high majority agreement in TimbreWM but substantially lower agreement in WMCodec. In a more sophisticated payload-aware setting, mixture weighting can further steer the decoder toward a selected nonmember, achieving a target success rate of 92.3% in TimbreWM. Preliminary confidence screening rejects many collusion-induced assignments while retaining most valid single-copy outputs. Code and results are available at https://github.com/Silwan5z/neural-audio-watermark-collusion-attack. This work highlights multi-copy traceability as an additional evaluation dimension for personalized neural audio watermarking alongside conventional single-copy robustness.