Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems

• URL: http://arxiv.org/abs/2509.09204v1
• Date: Thu, 11 Sep 2025 07:20:18 GMT
• Title: Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems
• Authors: Chin Yuen Kwok, Jia Qi Yip, Zhen Qiu, Chi Hung Chi, Kwok Yan Lam,
• Abstract summary: 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.
• Score: 26.00617832033757
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio deepfake detection (ADD) models are commonly evaluated using datasets that combine multiple synthesizers, with performance reported as a single Equal Error Rate (EER). However, this approach disproportionately weights synthesizers with more samples, underrepresenting others and reducing the overall reliability of EER. Additionally, most ADD datasets lack diversity in bona fide speech, often featuring a single environment and speech style (e.g., clean read speech), limiting their ability to simulate real-world conditions. To address these challenges, we propose bona fide cross-testing, a novel evaluation framework that incorporates diverse bona fide datasets and aggregates EERs for more balanced assessments. Our approach improves robustness and interpretability compared to traditional evaluation methods. We benchmark over 150 synthesizers across nine bona fide speech types and release a new dataset to facilitate further research at https://github.com/cyaaronk/audio_deepfake_eval.

Related papers

• Detecting and Rectifying Noisy Labels: A Similarity-based Approach [4.686586017523293]
  Label noise in datasets could significantly damage the performance and robustness of deep neural networks (DNNs) trained on these datasets.<n>We propose post-hoc, model-agnostic noise detection and rectification methods utilizing the penultimate feature from a DNN.<n>Our idea is based on the observation that the similarity between the penultimate feature of a mislabeled data point and its true class data points is higher than that for data points from other classes.
  arXiv  Detail & Related papers  (2025-09-28T16:41:56Z)
• Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection [7.402342914903391]
  Rehearsal with Auxiliary-Informed Sampling (RAIS) is a rehearsal-based CL approach for audio deepfake detection.<n>RAIS employs a label generation network to produce auxiliary labels, guiding diverse sample selection for the memory buffer.<n>Extensive experiments show RAIS outperforms state-of-the-art methods, achieving an average Equal Error Rate (EER) of 1.953 % across five experiences.
  arXiv  Detail & Related papers  (2025-05-30T11:40:50Z)
• End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation [8.11594945165255]
  We propose an end-to-end deep learning framework for audio deepfake detection that operates directly on raw waveforms.<n>Our model, RawNetLite, is a lightweight convolutional-recurrent architecture designed to capture both spectral and temporal features without handcrafted preprocessing.
  arXiv  Detail & Related papers  (2025-04-29T16:38:23Z)
• Where are we in audio deepfake detection? A systematic analysis over generative and detection models [59.09338266364506]
  SONAR is a synthetic AI-Audio Detection Framework and Benchmark.<n>It provides a comprehensive evaluation for distinguishing cutting-edge AI-synthesized auditory content.<n>It is the first framework to uniformly benchmark AI-audio detection across both traditional and foundation model-based detection systems.
  arXiv  Detail & Related papers  (2024-10-06T01:03:42Z)
• Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data [69.7174072745851]
  We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data.<n>To overcome the first challenge, we align the generations of the T2A model with the small-scale dataset using preference optimization.<n>To address the second challenge, we propose a novel caption generation technique that leverages the reasoning capabilities of Large Language Models.
  arXiv  Detail & Related papers  (2024-10-02T22:05:36Z)
• Bayesian Detector Combination for Object Detection with Crowdsourced Annotations [49.43709660948812]
  Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise. We propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations. BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models.
  arXiv  Detail & Related papers  (2024-07-10T18:00:54Z)
• Retrieval-Augmented Audio Deepfake Detection [27.13059118273849]
  We propose a retrieval-augmented detection framework that augments test samples with similar retrieved samples for enhanced detection. Experiments show the superior performance of the proposed RAD framework over baseline methods.
  arXiv  Detail & Related papers  (2024-04-22T05:46:40Z)
• 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)
• Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark [65.79402756995084]
  Real Acoustic Fields (RAF) is a new dataset that captures real acoustic room data from multiple modalities. RAF is the first dataset to provide densely captured room acoustic data.
  arXiv  Detail & Related papers  (2024-03-27T17:59:56Z)
• Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection [54.20974251478516]
  We propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting. When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. Our method can easily be generalized to related fields, like speech emotion recognition.
  arXiv  Detail & Related papers  (2023-08-07T05:05:49Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech [67.88748572167309]
  We present LDNet, a unified framework for mean opinion score (MOS) prediction. We propose two inference methods that provide more stable results and efficient computation.
  arXiv  Detail & Related papers  (2021-10-18T08:52:31Z)

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.