Dual-Granularity Orthogonal Disentanglement for Generalizable Audio Deepfake Detection

• URL: http://arxiv.org/abs/2606.16532v1
• Date: Mon, 15 Jun 2026 10:36:57 GMT
• Title: Dual-Granularity Orthogonal Disentanglement for Generalizable Audio Deepfake Detection
• Abstract summary: deepfake detectors often fail to generalize across speakers, as they learn speaker-identity features rather than synthesis artifacts.<n>This paper proposes a dual-granularity orthogonal disentanglement framework enforcing feature independence at two levels.<n> Experiments on ASVspoof 2019 LA, ASVspoof 2021 DF, and In-the-Wild datasets demonstrate that the proposed method achieves 1.35%, 7.88%, and 21.58% equal error rates.
• Score: 1.6262949941980935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audio deepfake detectors often fail to generalize across speakers, as they learn speaker-identity features rather than synthesis artifacts, known as implicit identity leakage. Existing methods address this but incur architectural complexity or training instability. This paper proposes a dual-granularity orthogonal disentanglement framework enforcing feature independence at two levels: sample-level cosine orthogonality captures directional decorrelation, while batch-level cross-covariance regularization eliminates linear correlations across embedding dimensions. A curriculum disentanglement schedule progressively strengthens the orthogonality constraint without auxiliary networks or adversarial dynamics. Experiments on ASVspoof 2019 LA, ASVspoof 2021 DF, and In-the-Wild datasets demonstrate that the proposed method achieves 1.35%, 7.88%, and 21.58% equal error rates (EER), respectively, surpassing gradient reversal disentanglement by 2.60% absolute on cross-dataset transfer.

Related papers

• Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data [0.5213778368155993]
  DIFFINT is an autoencoder whose latent bottleneck is structured as a set of soft, axis-aligned interval memberships.<n>It is the only interpretable detector in the statistically-tied leading cluster of seven methods.
  arXiv  Detail & Related papers  (2026-09-03T14:05:27Z)
• C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders [56.67585330425431]
  Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features.<n>These issues stem from inconsistent latent assignment across samples.<n>We introduce C$2$R, which penalizes the co-activation of directionally similar latents.
  arXiv  Detail & Related papers  (2026-06-29T17:45:31Z)
• Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity [7.28808693425028]
  vibration-based health monitoring of rotating machinery requires reliable fault diagnosis under operational data constraints.<n>We formulate feature alignment as a continuous-action Markov decision process solved via Proximal Policy Optimization.<n>An asymmetry-aware strategy reserves real data for the Normal class while augmenting fault classes with policy-aligned simulated samples.
  arXiv  Detail & Related papers  (2026-06-23T08:47:24Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs [5.018957704056544]
  Activation steering controls model behavior by modifying intermediate hidden states at inference time without retraining.<n>We show that when multiple semantic directions are superposed without constraints, the model collapses.<n>We propose GEMS, a training-free method that maps each source to a corresponding geometric constraint.
  arXiv  Detail & Related papers  (2026-06-18T08:43:33Z)
• DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion [5.766298616867406]
  Cross-modal 2D-3D gait recognition is impeded by inherent domain discrepancies between 2D silhouette and 3D LiDAR range-view representations.<n>We propose DiffCrossGait, which reformulates cross-modal matching as trajectory-level alignment in an identity-relevant latent diffusion space.
  arXiv  Detail & Related papers  (2026-05-29T04:56:15Z)
• Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series [24.192601578775186]
  We propose ContrastAD, an unsupervised framework that turns structural evolution into a learning signal rather than suppressing it.<n>Across five real-world benchmarks, ContrastAD attains the highest mean F1 and the highest AUC on three datasets.
  arXiv  Detail & Related papers  (2026-05-22T15:18:53Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.68391670109433]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• AdaptOVCD: Training-Free Open-Vocabulary Remote Sensing Change Detection via Adaptive Information Fusion [17.998110109161683]
  AdaptOVCD is a training-free Open-Vocabulary Change Detection architecture based on dual-dimensional multi-level information fusion.<n>The framework integrates multi-level information fusion across data, feature, and decision levels vertically while incorporating targeted adaptive designs horizontally.<n>It achieves 84.89% of the fully-supervised performance upper bound in cross-dataset evaluations and exhibits superior generalization capabilities.
  arXiv  Detail & Related papers  (2026-02-06T09:30:23Z)
• Refining Decision Boundaries In Anomaly Detection Using Similarity Search Within the Feature Space [3.3202103799131795]
  We introduce SDA2E, a Sparse Dual Adversarial Attention-based AutoEncoder designed to learn compact and discriminative latent representations from imbalanced, high-dimensional data.<n>We propose a similarity-guided active learning framework that integrates three novel strategies to refine decision boundaries efficiently.<n>We evaluate SDA2E extensively across 52 imbalanced datasets, including multiple DARPA Transparent Computing scenarios, and benchmark it against 15 state-of-the-art anomaly detection methods.
  arXiv  Detail & Related papers  (2026-02-02T23:55:08Z)
• Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification [55.56234913868664]
  We propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD) for reliable learning on multimodal data.<n>The proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
  arXiv  Detail & Related papers  (2026-01-12T03:14:12Z)
• SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection [6.042897432654865]
  Spectral-cONtrastive Audio Residuals (AR) is a frequency-guided framework for deepfake audio detectors.<n>AR disentangles an audio signal into complementary representations.<n> evaluated on the ASVspoof 2021 and in-the-wild benchmarks.
  arXiv  Detail & Related papers  (2025-11-26T12:16:38Z)
• Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching [55.784713740698365]
  Unsupervised stereo matching has garnered significant attention for its independence from costly disparity annotations.<n>A feasible solution lies in transferring 3D geometric knowledge from a relative depth map to the stereo matching networks.<n>This work proposes a novel unsupervised learning framework to address these challenges.
  arXiv  Detail & Related papers  (2025-08-02T09:11:05Z)
• G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation [49.421099172544196]
  We propose a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels. We also introduce contrastive distillation to effectively capture the information encoded in the relationship between different feature regions. Our method consistently outperforms the existing detection KD techniques, and works when (1) components in the framework are used separately and in conjunction.
  arXiv  Detail & Related papers  (2021-08-17T07:44:27Z)
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification [49.86640645460706]
  In this study, we investigate various methods to capture discriminative information and simultaneously mitigate the overfitting problem. We adopt a max feature map method to replace conventional non-linear activations in a deep neural network. Two data augment methods and two deep architecture modules are further explored to reduce overfitting and sustain the system's discriminative power.
  arXiv  Detail & Related papers  (2020-07-09T08:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.