研究人员正在开发先进的音频深度伪造检测方法，重点是提高泛化能力和可解释性。一种名为SONAR的方法利用频率引导框架来利用合成音频中的高频伪影，取得了最先进的性能。另一种方法采用维纳-霍普夫线性预测结合轻量级CNN，创建了一个可解释的检测系统，该系统在较低的复杂性下保持了具有竞争力的准确性。此外，一个使用大型音频语言模型的受人类启发的推理框架旨在为深度伪造分类提供更具可解释性的理由，而其他研究则调查了检测模型中的性别偏见，并提出了结合空间和频率特征的融合框架以增强鲁棒性。
AI
arXiv:2511.21325v2 Announce Type: replace-cross Abstract: Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs. A central reason is spectral bias, the tendency of neural networks to learn low-frequency structure before high-frequency (HF) detai…
arXiv cs.AI
TIER_1English(EN)·Mattia Tamiazzo, Simone Milani, Massimo Iuliani, Marco Fontani·
arXiv:2607.12584v1 Announce Type: cross Abstract: The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics. While recent approaches achieve high detection accuracy, they typically rely on black-box…
The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics. While recent approaches achieve high detection accuracy, they typically rely on black-box architectures that offer limited interpretability…
The rapid advancement of synthetic speech generation methods has made audio deepfake detection a critical challenge in multimedia forensics. While recent approaches achieve high detection accuracy, they typically rely on black-box architectures that offer limited interpretability…
arXiv:2603.10725v3 Announce Type: replace-cross Abstract: The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information. To mitigate this issue, speech deepfake detection (SDD)…
arXiv cs.AI
TIER_1English(EN)·Aishwarya R. Fursule, Vamshi Nallaguntla, Shruti Kshirsagar, Anderson R. Avila·
arXiv:2607.09891v1 Announce Type: cross Abstract: Audio deepfake detection models determine whether speech is genuine or artificially generated, but high overall accuracy can mask substantial performance disparities across demographic groups. In this work, we investigate gender b…
arXiv cs.CV
TIER_1Nederlands(NL)·Abhijeet Narang, Kartik Kuckreja, Shreya Ghosh, Muhammad Haris Khan, Usman Tariq, Jianfei Cai, Abhinav Dhall·
arXiv:2607.21007v1 Announce Type: new Abstract: Deepfake detection is moving beyond binary classification decisions toward systems that can also explain the visual evidence supporting those decisions. This transition is important for real-world verification settings, where divers…
arXiv cs.CV
TIER_1English(EN)·Pamela Kirui, Cho Hyuk, Qingzhong Liu, Haodi Jiang·
arXiv:2607.17441v1 Announce Type: new Abstract: Deepfake generation has raised growing concerns regarding digital media authenticity, misinformation, identity fraud, and public trust. Recent studies show that combining spatial and frequency features leads to stronger detection re…
Audio deepfake detector uses Wiener-Hopf math for explainable AI A new arXiv preprint pairs Wiener-Hopf linear prediction with a lightweight CNN to detect synthetic speech and explain why it was flagged. https://www. notatechguy.com/audio-deepfake -detector-uses-wiener-hopf-math-…
