Asymmetric Phase Coding Audio Watermarking
Abstract
The proliferation of deepfake audio challenges voice-based authentication systems; passive forensic detectors are sensitive to evolving generative models and to real-world channel distortions. We propose Asymmetric Phase Coding (APC), a training-free cryptographic signing layer for audio, designed as a compact and auditable provenance primitive that can stand alone or be stacked with learned watermarks. APC combines Ed25519 digital signatures (EdDSA, FIPS 186-5; 64-byte signatures) with Reed-Solomon error correction, pseudo-random STFT phase-bin selection, and a redundant quantization-index-modulation (QIM) code on log-magnitude differences of adjacent bin pairs, yielding a compact, non-repudiable, blind-extractable watermark. We evaluate APC on 1,000 LibriSpeech test-clean clips (10 s each, 44.1 kHz) under eight attack configurations -- identity, 10% end-cropping, 20% end-cropping, 8 kHz low-pass, 16 kHz round-trip resampling, FLAC re-encoding, MP3 at 128 kbps, and OGG-Vorbis at 128 kbps -- and achieve cryptographic verification rates between 97.5% and 98.3% on every condition at mean PESQ=3.02 and tens-of-milliseconds CPU latency. We explicitly compare APC against recent neural baselines (AudioSeal, WavMark, SilentCipher), detail the threat model (forgery resistance vs. erasure), characterize the dataset, define all metrics, quantify an adaptive white-box erasure attack, and release code, keys, and metadata for reproducibility.
The following analysis is generated by AI and may contain errors. It is separate from the authors’ abstract and is not peer review.
Research summary
The paper presents Asymmetric Phase Coding (APC), a novel training-free audio watermarking technique that integrates cryptographic signing to enhance audio authenticity. This work significantly contributes to the field by addressing the challenges posed by deepfake audio and providing a robust solution that combines security and usability in audio watermarking.
Methodology
The methodology is robust, employing a hybrid approach that combines cryptographic signing with audio watermarking techniques. The use of Ed25519 digital signatures and Reed-Solomon error correction enhances the reliability of the watermarking process. The choice of pseudo-random STFT phase-bin selection and redundant quantization-index modulation (QIM) reflects a thoughtful design aimed at ensuring imperceptibility and robustness against various audio attacks. The training-free nature of the method is particularly noteworthy, as it allows for immediate application without the need for extensive datasets or computational resources.
Results & evaluation
The experiments are comprehensive, utilizing a substantial dataset of 1,000 LibriSpeech clips and evaluating performance across eight distinct attack configurations. The reported cryptographic verification rates of 97.5% to 98.3% under various conditions demonstrate the effectiveness of the proposed method. The inclusion of multiple metrics, such as PESQ and CPU latency, provides a well-rounded view of the method's performance, although further subjective evaluations could enhance the findings.
Reproducibility
The authors have made significant efforts to ensure reproducibility by releasing code, keys, and metadata. The detailed description of the experimental setup, including the specific parameters used for embedding and extraction, supports this goal. However, the absence of a direct URL for the project limits accessibility.
Limitations
The paper acknowledges limitations, including performance degradation on clips with sparse spectral content and the fixed mapping from bits to phase, which could be optimized. Additionally, the evaluation does not consider more sophisticated adversarial attacks beyond the white-box phase randomization.
Broader impact
The proposed APC method has significant implications for audio authentication and integrity verification in various applications, particularly in contexts where audio content is susceptible to manipulation, such as media distribution and digital forensics. Its ability to provide non-repudiable authentication without requiring training data positions it as a valuable tool in the fight against deepfake audio. The paper presents Asymmetric Phase Coding (APC), a novel training-free audio watermarking technique that integrates cryptographic signing to enhance audio authenticity. This work significantly contributes to the field by addressing the challenges posed by deepfake audio and providing a robust solution that combines security and usability in audio watermarking.
Author of this paper? Send a correction.