HierCon: Hierarchical Contrastive Attention for Audio Deepfake Detection

• URL: http://arxiv.org/abs/2602.01032v1
• Date: Sun, 01 Feb 2026 05:36:32 GMT
• Title: HierCon: Hierarchical Contrastive Attention for Audio Deepfake Detection
• Authors: Zhili Nicholas Liang, Soyeon Caren Han, Qizhou Wang, Christopher Leckie,
• Abstract summary: Audio deepfakes generated by modern TTS and voice conversion systems are increasingly difficult to distinguish from real speech, raising serious risks for security and online trust.<n>We propose HierCon, a hierarchical layer attention framework combined with margin-based contrastive learning that models dependencies across temporal frames, neighbouring layers, and layer groups, while encouraging domain-invariant embeddings.
• Score: 21.083747008336175
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio deepfakes generated by modern TTS and voice conversion systems are increasingly difficult to distinguish from real speech, raising serious risks for security and online trust. While state-of-the-art self-supervised models provide rich multi-layer representations, existing detectors treat layers independently and overlook temporal and hierarchical dependencies critical for identifying synthetic artefacts. We propose HierCon, a hierarchical layer attention framework combined with margin-based contrastive learning that models dependencies across temporal frames, neighbouring layers, and layer groups, while encouraging domain-invariant embeddings. Evaluated on ASVspoof 2021 DF and In-the-Wild datasets, our method achieves state-of-the-art performance (1.93% and 6.87% EER), improving over independent layer weighting by 36.6% and 22.5% respectively. The results and attention visualisations confirm that hierarchical modelling enhances generalisation to cross-domain generation techniques and recording conditions.

Related papers

• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise [12.720216418233795]
  We propose a novel framework termed Quality-Aware Robust Multi-View Clustering (QARMVC)<n>QARMVC employs an information bottleneck mechanism to extract intrinsic semantics for view reconstruction.<n>In experiments on five benchmark datasets, QARMVC consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-26T03:16:44Z)
• Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models [13.707653566827704]
  Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret.<n>Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification.<n>We propose a unified hierarchical attribution framework that computes layer-wise Integrated Gradients within each Transformer block and fuses these token-level attributions with class-specific attention gradients.
  arXiv  Detail & Related papers  (2026-02-18T17:03:10Z)
• Audio Deepfake Detection in the Age of Advanced Text-to-Speech models [0.0]
  Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech.<n>Recent advances in Text-to-Speech (TTS) systems have substantially increased the realism of synthetic speech.
  arXiv  Detail & Related papers  (2026-01-28T11:39:40Z)
• 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)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling [65.02357548201188]
  We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning.<n>Our framework operates by synthesizing the desired separated sound spectrograms directly from a noise distribution, conditioned concurrently on the mixed audio input and associated visual information.
  arXiv  Detail & Related papers  (2025-09-26T08:46:00Z)
• HierCVAE: Hierarchical Attention-Driven Conditional Variational Autoencoders for Multi-Scale Temporal Modeling [7.900277891102576]
  Temporal modeling in complex systems requires capturing dependencies across multiple time scales.<n>We propose HierCVAE, a novel architecture that integrates hierarchical attention mechanisms with conditional variational autoencoders.
  arXiv  Detail & Related papers  (2025-08-26T10:55:35Z)
• Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection [30.77558600436759]
  ARAS is a language-conditioned, auto-regressive anomaly synthesis approach.<n>It injects local, text-specified defects into normal images via token-anchored latent editing.<n>It significantly enhances defect realism, preserves fine-grained material textures, and provides continuous semantic control over synthesized anomalies.
  arXiv  Detail & Related papers  (2025-08-05T15:07:32Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection [4.908389661988192]
  HFMF is a comprehensive two-stage deepfake detection framework.<n>It integrates vision Transformers and convolutional nets through a hierarchical feature fusion mechanism.<n>We demonstrate that our architecture achieves superior performance across diverse dataset benchmarks.
  arXiv  Detail & Related papers  (2025-01-10T00:20:29Z)
• Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023 [51.95161901441527]
  In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. Deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Our final system achieves state-of-the-art performance and ranks third on the leaderboard on MER-MULTI sub-challenge.
  arXiv  Detail & Related papers  (2023-09-11T03:19:10Z)
• Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection [7.324459578044212]
  Face presentation attack detection (PAD) is attracting a lot of attention and playing a key role in securing face recognition systems. We propose a dual-stream convolution neural networks (CNNs) framework to deal with unseen scenarios. We successfully prove the design of our proposed PAD solution in a step-wise ablation study.
  arXiv  Detail & Related papers  (2021-09-16T13:06:43Z)

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.