Open environment oriented open set model attribution of deepfake audio is an emerging research topic, aiming to identify the generation models of deepfake audio. Most previous work requires manually setting a rejection threshold for unknown classes to compare with predicted probabilities. However, models often overfit training instances and generate overly confident predictions. Moreover, thresholds that effectively distinguish unknown categories in the current dataset may not be suitable for identifying known and unknown categories in another data distribution. To address the issues, we propose a novel framework for open set model attribution of deepfake audio with rejection threshold adaptation (ReTA). Specifically, the reconstruction error learning module trains by combining the representation of system fingerprints with labels corresponding to either the target class or a randomly chosen other class label. This process generates matching and non-matching reconstructed samples, establishing the reconstruction error distributions for each class and laying the foundation for the reject threshold calculation module. The reject threshold calculation module utilizes gaussian probability estimation to fit the distributions of matching and non-matching reconstruction errors. It then computes adaptive reject thresholds for all classes through probability minimization criteria. The experimental results demonstrate the effectiveness of ReTA in improving the open set model attributes of deepfake audio.

翻译：面向开放环境的深度伪造音频开放集模型溯源是一个新兴的研究课题，旨在识别深度伪造音频的生成模型。以往大多数工作需要为未知类别手动设置拒绝阈值，以与预测概率进行比较。然而，模型常常对训练实例过拟合并产生过于自信的预测。此外，在当前数据集中能有效区分未知类别的阈值，可能并不适用于识别另一数据分布中的已知与未知类别。为解决这些问题，我们提出了一种新颖的、带有拒绝阈值自适应（ReTA）的深度伪造音频开放集模型溯源框架。具体而言，重构误差学习模块通过结合系统指纹表示与对应目标类别或随机选取的其他类别标签进行训练。该过程生成匹配与非匹配的重构样本，为每个类别建立重构误差分布，并为拒绝阈值计算模块奠定基础。拒绝阈值计算模块利用高斯概率估计来拟合匹配与非匹配重构误差的分布，随后通过概率最小化准则为所有类别计算自适应的拒绝阈值。实验结果证明了ReTA在提升深度伪造音频开放集模型溯源性能方面的有效性。