Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR

• URL: http://arxiv.org/abs/2603.06164v1
• Date: Fri, 06 Mar 2026 11:16:55 GMT
• Title: Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR
• Abstract summary: Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone.<n>We present a controlled study of compact SSL backbones from the HuBERT and WavLM within a unified pairwise-gated fusion detector.<n>We show that multilingual HuBERT pre-training is the primary driver of cross-domain robustness, enabling 100M models to match larger and commercial systems.
• Score: 30.327041194397022
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated Transformer for Out-of-domain Recognition a controlled study of compact SSL backbones from the HuBERT and WavLM within a unified pairwise-gated fusion detector, evaluated across 14 cross-domain benchmarks. We show that multilingual HuBERT pre-training is the primary driver of cross-domain robustness, enabling 100M models to match larger and commercial systems. Beyond EER, we introduce a test-time augmentation protocol with perturbation-based aleatoric uncertainty to expose calibration differences invisible to standard metrics: WavLM variants exhibit overconfident miscalibration under perturbation, whereas iterative mHuBERT remains stable. These findings indicate that SSL pre-training trajectory, not model scale, drives reliable audio deepfake detection.

Related papers

• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation [18.70132691409063]
  Test-Time Adaptation aims to mitigate distributional shifts between training and test domains during inference time.<n>The coupling of domain and semantic shifts often collapses the feature space, severely degrading both classification and out-of-distribution detection.<n>We propose DOmain COmpensation (DOCO), a lightweight and effective framework that robustly performs domain adaptation and OOD detection in a synergistic, closed loop.
  arXiv  Detail & Related papers  (2026-04-23T15:29:29Z)
• Tracing the Chain: Deep Learning for Stepping-Stone Intrusion Detection [7.981257687111937]
  Stepping-stone intrusions (SSIs) are a prevalent network evasion technique.<n>Effective SSI detection requires correlating the incoming and outgoing flows at each relay host at extremely low false positive rates.<n> ESPRESSO is a flow correlation model combining a transformer-based feature extraction network, time-aligned multi-channel interval features, and online triplet metric learning.
  arXiv  Detail & Related papers  (2026-04-09T22:26:52Z)
• Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference [3.3323431541048385]
  We present a verification framework and protocol that replaces full proofs with a lightweight, sampling-based approach.<n>We formalize the conditions under which trace separation between functionally dissimilar models can be leveraged to argue the security of verifiable inference protocols.<n>Our approach reduces proving times by several orders of magnitude compared to state-of-the-art cryptographic proof systems.
  arXiv  Detail & Related papers  (2026-03-19T15:24:27Z)
• A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection [2.432576583937997]
  Spoof-SUPERB is a benchmark for audio deepfake detection.<n>We evaluate 20 SSL models spanning generative, discriminative, and spectrogram-based architectures.
  arXiv  Detail & Related papers  (2026-03-02T05:45:55Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs [0.6345523830122167]
  Large language models can exhibit surprising adapter interference when combining domain adaptation and instruction alignment.<n>We study a two-stage LoRA pipeline for medical LLMs, where domain-oriented pre-training (PT) and supervised fine-tuning (SFT) are trained separately and later merged.
  arXiv  Detail & Related papers  (2026-01-26T10:54:06Z)
• Entropy-Guided Agreement-Diversity: A Semi-Supervised Active Learning Framework for Fetal Head Segmentation in Ultrasound [4.594829845106234]
  We propose a two-stage Active Learning sampler, Entropy-Guided Agreement-Diversity (EGAD) for fetal head segmentation.<n>In experiments, SSL-EGAD achieves an average Dice score of 94.57% and 96.32% on two public datasets for fetal head segmentation.
  arXiv  Detail & Related papers  (2026-01-24T13:23:18Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• Cross-Attention with Confidence Weighting for Multi-Channel Audio Alignment [5.380078543698624]
  Multi-channel audio alignment is a key requirement in bioacoustic monitoring, spatial audio systems, and acoustic localization.<n>We introduce a method that combines cross-attention mechanisms with confidence-weighted scoring to improve multi-channel audio synchronization.<n>Our method achieved first place in the BioDCASE 2025 Task 1 challenge with 0.30 MSE average across test datasets, compared to 0.58 for the deep learning baseline.
  arXiv  Detail & Related papers  (2025-09-21T05:14:06Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Benchmark for Uncertainty & Robustness in Self-Supervised Learning [0.0]
  Self-Supervised Learning is crucial for real-world applications, especially in data-hungry domains such as healthcare and self-driving cars. In this paper, we explore variants of SSL methods, including Jigsaw Puzzles, Context, Rotation, Geometric Transformations Prediction for vision, as well as BERT and GPT for language tasks. Our goal is to create a benchmark with outputs from experiments, providing a starting point for new SSL methods in Reliable Machine Learning.
  arXiv  Detail & Related papers  (2022-12-23T15:46:23Z)
• Mitigating the Mutual Error Amplification for Semi-Supervised Object Detection [92.52505195585925]
  We propose a Cross Teaching (CT) method, aiming to mitigate the mutual error amplification by introducing a rectification mechanism of pseudo labels. In contrast to existing mutual teaching methods that directly treat predictions from other detectors as pseudo labels, we propose the Label Rectification Module (LRM)
  arXiv  Detail & Related papers  (2022-01-26T03:34:57Z)
• Spotting adversarial samples for speaker verification by neural vocoders [102.1486475058963]
  We adopt neural vocoders to spot adversarial samples for automatic speaker verification (ASV) We find that the difference between the ASV scores for the original and re-synthesize audio is a good indicator for discrimination between genuine and adversarial samples. Our codes will be made open-source for future works to do comparison.
  arXiv  Detail & Related papers  (2021-07-01T08:58:16Z)

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.