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.
Wavmark: Watermarking for audio generation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
LAVA is a layered audio-visual watermarking system using cross-modal fusion and calibration-aware alignment to achieve robust deepfake tamper detection and localization under compression and asynchrony.
APC embeds compact Ed25519 signatures into audio phase data with error correction to achieve 97.5-98.3% cryptographic verification under eight attack types at mean PESQ 3.02.
AI content watermarking exhibits detection disparities across languages, cultures, and demographics due to content-dependent signal properties, with benchmarks failing to disaggregate performance and watermarking held to lower fairness standards than generative models.
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.
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
-
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.
-
LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization
LAVA is a layered audio-visual watermarking system using cross-modal fusion and calibration-aware alignment to achieve robust deepfake tamper detection and localization under compression and asynchrony.
-
Asymmetric Phase Coding Audio Watermarking
APC embeds compact Ed25519 signatures into audio phase data with error correction to achieve 97.5-98.3% cryptographic verification under eight attack types at mean PESQ 3.02.
-
Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking
AI content watermarking exhibits detection disparities across languages, cultures, and demographics due to content-dependent signal properties, with benchmarks failing to disaggregate performance and watermarking held to lower fairness standards than generative models.
-
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.
-
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.