AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

• URL: http://arxiv.org/abs/2603.26856v1
• Date: Fri, 27 Mar 2026 13:36:11 GMT
• Title: AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection
• Abstract summary: Artifact-Focused Self-Synthesis (AFSS) is a method designed to generate pseudo-fake samples from real audio.<n>AFSS enforces same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content.<n>AFSS achieves state-of-the-art performance with an average EER of 5.45%, including a significant reduction to 1.23% on WaveFake and 2.70% on In-the-Wild.
• Score: 1.1091582432763736
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused Self-Synthesis (AFSS), a method designed to mitigate this bias by generating pseudo-fake samples from real audio via two mechanisms: self-conversion and self-reconstruction. The core insight of AFSS lies in enforcing same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content. This forces the detector to focus exclusively on generation artifacts rather than irrelevant confounding factors. Furthermore, we introduce a learnable reweighting loss to dynamically emphasize synthetic samples during training. Extensive experiments across 7 datasets demonstrate that AFSS achieves state-of-the-art performance with an average EER of 5.45\%, including a significant reduction to 1.23\% on WaveFake and 2.70\% on In-the-Wild, all while eliminating the dependency on pre-collected fake datasets. Our code is publicly available at https://github.com/NguyenLeHaiSonGit/AFSS.

Related papers

• Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems [26.00617832033757]
  We propose bona fide cross-testing, a novel evaluation framework that incorporates diverse bona fide datasets and aggregates EERs for more balanced assessments.<n>We benchmark over 150 synthesizers across nine bona fide speech types and release a new dataset to facilitate further research.
  arXiv  Detail & Related papers  (2025-09-11T07:20:18Z)
• Crucial-Diff: A Unified Diffusion Model for Crucial Image and Annotation Synthesis in Data-scarce Scenarios [65.97836905826145]
  scarcity of data in various scenarios, such as medical, industry and autonomous driving, leads to model overfitting and dataset imbalance.<n>We propose Crucial-Diff, a domain-agnostic framework designed to synthesize crucial samples.<n>Our framework generates diverse, high-quality training data, achieving a pixel-level AP of 83.63% and an F1-MAX of 78.12% on MVTec.
  arXiv  Detail & Related papers  (2025-07-14T04:41:38Z)
• Statistics-aware Audio-visual Deepfake Detector [11.671275975119089]
  Methods in audio-visualfake detection mostly assess the synchronization between audio and visual features. We propose a statistical feature loss to enhance the discrimination capability of the model. Experiments on the DFDC and FakeAVCeleb datasets demonstrate the relevance of the proposed method.
  arXiv  Detail & Related papers  (2024-07-16T12:15:41Z)
• Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models [52.04189118767758]
  Generalization is a main issue for current audio deepfake detectors. In this paper we study the potential of large-scale pre-trained models for audio deepfake detection.
  arXiv  Detail & Related papers  (2024-05-03T15:27:11Z)
• Cross-Domain Audio Deepfake Detection: Dataset and Analysis [11.985093463886056]
  Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. We construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models.
  arXiv  Detail & Related papers  (2024-04-07T10:10:15Z)
• From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition [64.59093444558549]
  We propose a simple, easy-to-implement, two-step training pipeline that we call From Fake to Real. By training on real and synthetic data separately, FFR does not expose the model to the statistical differences between real and synthetic data. Our experiments show that FFR improves worst group accuracy over the state-of-the-art by up to 20% over three datasets.
  arXiv  Detail & Related papers  (2023-08-08T19:52:28Z)
• Fully Automated End-to-End Fake Audio Detection [57.78459588263812]
  This paper proposes a fully automated end-toend fake audio detection method. We first use wav2vec pre-trained model to obtain a high-level representation of the speech. For the network structure, we use a modified version of the differentiable architecture search (DARTS) named light-DARTS.
  arXiv  Detail & Related papers  (2022-08-20T06:46:55Z)
• Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models [13.456066434598155]
  We address the problem of detecting speech directed to a device that does not contain a specific wake-word. Specifically, we focus on audio coming from a touch-based invocation.
  arXiv  Detail & Related papers  (2022-03-30T01:27:39Z)
• Voice-Face Homogeneity Tells Deepfake [56.334968246631725]
  Existing detection approaches contribute to exploring the specific artifacts in deepfake videos. We propose to perform the deepfake detection from an unexplored voice-face matching view. Our model obtains significantly improved performance as compared to other state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-03-04T09:08:50Z)
• Continual Learning for Fake Audio Detection [62.54860236190694]
  This paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. Experiments are conducted on the ASVspoof 2019 dataset.
  arXiv  Detail & Related papers  (2021-04-15T07:57:05Z)
• Suppressing Uncertainties for Large-Scale Facial Expression Recognition [81.51495681011404]
  This paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial images. Results on public benchmarks demonstrate that our SCN outperforms current state-of-the-art methods with textbf88.14% on RAF-DB, textbf60.23% on AffectNet, and textbf89.35% on FERPlus.
  arXiv  Detail & Related papers  (2020-02-24T17:24:36Z)

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.