LambdaMark is the first generic radioactive audio watermark that injects multi-bit messages into semantic latent representations, achieving robustness to distortions and removal attacks even after downstream model finetuning.
Wavmark: Watermarking for audio generation
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
MelShield adds keyed low-energy spread-spectrum perturbations to Mel-spectrograms inside TTS pipelines before vocoding to enable robust extraction of user-specific attribution signals even after compression or noise.
Introduces AWM adaptive attack using two-stage optimization and distribution estimation to bypass audio watermark detectors with low detection rates on voice datasets.
DiffErase removes black-box audio watermarks via diffusion priors by adding intermediate noise and regenerating with a pretrained model, preserving quality across audio domains.
A training-free audio watermarking method that reduces vocabulary via community detection to boost detection robustness by orders of magnitude while resisting audio modifications.
Major watermarking benchmarks omit cross-lingual, cultural, and demographic reporting, creating a pluralistic evaluation gap that current governance mandates ignore.
StreamMark trains an Encoder-Distortion-Decoder network to embed semi-fragile watermarks that remain recoverable after benign audio transformations but drop to random accuracy under voice conversion and editing attacks.
A black-box audio watermark removal attack trained on limited samples that generalizes across datasets and watermark schemes with high attack success rates.
Feature-aligned watermarking embeds a codec-generated pseudo-speech signal into the spectrogram to raise robustness against reconstruction models while keeping imperceptibility comparable to prior methods.
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
citing papers explorer
-
LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity
LambdaMark is the first generic radioactive audio watermark that injects multi-bit messages into semantic latent representations, achieving robustness to distortions and removal attacks even after downstream model finetuning.
-
MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
MelShield adds keyed low-energy spread-spectrum perturbations to Mel-spectrograms inside TTS pipelines before vocoding to enable robust extraction of user-specific attribution signals even after compression or noise.
-
Learning to Evade: Adaptive Attacks on Audio Watermarking
Introduces AWM adaptive attack using two-stage optimization and distribution estimation to bypass audio watermark detectors with low detection rates on voice datasets.
-
Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
DiffErase removes black-box audio watermarks via diffusion priors by adding intermediate noise and regenerating with a pretrained model, preserving quality across audio domains.
-
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
A training-free audio watermarking method that reduces vocabulary via community detection to boost detection robustness by orders of magnitude while resisting audio modifications.
-
Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking
Major watermarking benchmarks omit cross-lingual, cultural, and demographic reporting, creating a pluralistic evaluation gap that current governance mandates ignore.
-
StreamMark: A Deep Learning-Based Semi-Fragile Audio Watermarking for Proactive Deepfake Detection
StreamMark trains an Encoder-Distortion-Decoder network to embed semi-fragile watermarks that remain recoverable after benign audio transformations but drop to random accuracy under voice conversion and editing attacks.
-
HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal
A black-box audio watermark removal attack trained on limited samples that generalizes across datasets and watermark schemes with high attack success rates.
-
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
Feature-aligned watermarking embeds a codec-generated pseudo-speech signal into the spectrogram to raise robustness against reconstruction models while keeping imperceptibility comparable to prior methods.
-
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
- The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
- Asymmetric Phase Coding Audio Watermarking
- LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization