SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection

TL;DR

SONAR introduces a frequency-guided contrastive framework that disentangles and leverages high-frequency residuals in audio to improve deepfake detection, achieving state-of-the-art results and faster convergence.

Contribution

The paper proposes a novel spectral contrastive approach that explicitly disentangles low- and high-frequency audio features for enhanced deepfake detection.

Findings

Achieves state-of-the-art performance on ASVspoof 2021 and in-the-wild benchmarks.

Converges four times faster than strong baseline models.

Unveils a frequency-guided contrastive learning framework that is architecture-agnostic.

Abstract

Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs. A central reason is spectral bias, the tendency of neural networks to learn low-frequency structure before high-frequency (HF) details, which both causes DF generators to leave HF artifacts and leaves those same artifacts under-exploited by common detectors. To address this gap, we propose Spectral-cONtrastive Audio Residuals (SONAR), a frequency-guided framework that explicitly disentangles an audio signal into complementary representations. An XLSR encoder captures the dominant low-frequency content, while the same cloned path, preceded by learnable SRM, value-constrained high-pass filters, distills faint HF residuals. Frequency cross-attention reunites the two views for long- and short-range frequency dependencies, and a frequency-aware Jensen-Shannon contrastive loss pulls real content-noise pairs together while pushing fake embeddings apart, accelerating optimization and sharpening decision boundaries. Evaluated on the ASVspoof 2021 and in-the-wild benchmarks, SONAR attains state-of-the-art performance and converges four times faster than strong baselines. By elevating faint high-frequency residuals to first-class learning signals, SONAR unveils a fully data-driven, frequency-guided contrastive framework that splits the latent space into two disjoint manifolds: natural-HF for genuine audio and distorted-HF for synthetic audio, thereby sharpening decision boundaries. Because the scheme operates purely at the representation level, it is architecture-agnostic and, in future work, can be seamlessly integrated into any model or modality where subtle high-frequency cues are decisive.