English(EN)Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection
新研究通过跨语言和多模态方法解决深度伪造检测问题 · 跟踪4个来源
作者PulseAugur 编辑部·[7 个来源]·
研究人员正在开发先进的音频和视频深度伪造检测方法，重点是提高跨不同语言和未见攻击类型的泛化能力。一种名为“语言正交化”的方法旨在从语音模型中去除特定语言的变体，以增强跨语言检测能力。另一种名为CRAF的方法融合了来自自监督学习模型和听觉大语言模型的互补表示，以提高鲁棒性。此外，R2M提供了一个无需训练的框架，通过分离共享组件和生成器特定的伪影来合并深度伪造检测模型，而MARE则利用带有强化学习的视觉-语言模型来创建可解释的深度伪造检测系统。
AI
arXiv:2609.19818v1 Announce Type: cross Abstract: Generalizing to unseen attacks remains challenging for audio deepfake detectors, and collecting training data covering all potential attacks is impractical. We explore recurrent refinement in an already-trained SSL-based detector …
arXiv:2609.20063v1 Announce Type: cross Abstract: The rapid advancement of speech synthesis and voice conversion technologies has made audio deepfakes increasingly realistic, posing serious security risks in practical applications. While existing detection methods achieve strong …
arXiv cs.CL
TIER_1English(EN)·Minu Kim, Ji Sub Um, Hoirin Kim·
arXiv:2609.16458v1 Announce Type: cross Abstract: Audio deepfake detectors need to transfer to languages absent from training, as multilingual speech synthesis outpaces labeled anti-spoofing resources. While detectors increasingly rely on self-supervised speech models (S3Ms), the…
arXiv:2609.13842v1 Announce Type: cross Abstract: Recent advances in speech synthesis and voice conversion have made deepfake speech increasingly realistic, making generalization to unseen spoofing attacks a critical challenge. Pretrained speech and audio models offer a promising…
Audio deepfake detectors need to transfer to languages absent from training, as multilingual speech synthesis outpaces labeled anti-spoofing resources. While detectors increasingly rely on self-supervised speech models (S3Ms), these backbones encode language-dependent structure t…
arXiv cs.CV
TIER_1English(EN)·Jinhee Park, Guisik Kim, Choongsang Cho, Junseok Kwon·
arXiv:2509.24367v2 Announce Type: replace Abstract: Deepfake generators evolve rapidly, making exhaustive data collection and repeated retraining impractical. Unlike generic multi-task settings, deepfake specialists share a common binary objective (Real vs. Fake) and mainly diffe…
arXiv:2601.20433v4 Announce Type: replace Abstract: Deepfake detection is a widely researched topic that is crucial for combating the spread of malicious content, with existing methods mainly modeling the problem as classification or spatial localization. The rapid advancements i…
