统计感知的音视频深度伪造检测器
Statistics-aware Audio-visual Deepfake Detector
AI总结：
提出一种统计感知的音视频深度伪造检测方法，通过统计特征损失、波形表示、分数归一化和浅层网络，在DFDC和FakeAVCeleb数据集上验证了有效性。
摘要：
在本文中，我们提出了一种增强的音视频深度伪造检测方法。近期音视频深度伪造检测方法大多评估音频与视觉特征之间的同步性。尽管这些方法已展现出有前景的结果，但它们基于孤立特征距离的最大化/最小化，未考虑特征统计信息。此外，它们依赖繁琐的深度学习架构，并严重依赖于经验性固定的超参数。为克服这些局限，我们提出：（1）一种统计特征损失，以增强模型的判别能力，而非仅依赖特征距离；（2）使用波形描述音频，替代基于频率的表示；（3）对伪造分数进行后处理归一化；（4）使用更浅的网络以降低计算复杂度。在DFDC和FakeAVCeleb数据集上的实验证明了所提方法的有效性。
英文摘要：
In this paper, we propose an enhanced audio-visual deep detection method. Recent methods in audio-visual deepfake detection mostly assess the synchronization between audio and visual features. Although they have shown promising results, they are based on the maximization/minimization of isolated feature distances without considering feature statistics. Moreover, they rely on cumbersome deep learning architectures and are heavily dependent on empirically fixed hyperparameters. Herein, to overcome these limitations, we propose: (1) a statistical feature loss to enhance the discrimination capability of the model, instead of relying solely on feature distances; (2) using the waveform for describing the audio as a replacement of frequency-based representations; (3) a post-processing normalization of the fakeness score; (4) the use of shallower network for reducing the computational complexity. Experiments on the DFDC and FakeAVCeleb datasets demonstrate the relevance of the proposed method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
