针对语音伪造检测的持续学习难题，提出按神经元重要性分区域优化的新方法。
Region-Based Optimization in Continual Learning for Audio Deepfake Detection
- 根据费雪信息矩阵划分神经元区域，分区域进行差异化优化。
- 在真实与伪造语音检测上分别采用平行或正交梯度更新，提升适应能力。
- 结合遗忘机制释放冗余神经元，适合需要长期更新的检测任务。
语音合成与语音转换技术快速发展，带来便利的同时也引发新的安全风险，亟需有效的音频深度伪造检测手段。尽管现有模型表现良好，但在面对现实世界中多样化、不断演变的伪造形式时，性能下降明显。为此，我们提出一种名为基于区域优化（RegO）的持续学习方法，用于音频深度伪造检测。通过费雪信息矩阵识别对真实与伪造音频检测均重要的神经元区域，并将其划分为四类：对真实音频重要的区域、对伪造音频重要的区域、两者共有的区域以及不重要的区域。对于不重要的区域，直接微调以快速适应新任务；对仅影响真实音频检测的区域，采用并行梯度优化；对仅影响伪造音频检测的区域，采用正交方向优化；对共同重要的区域，则使用样本比例自适应的梯度优化策略。该区域自适应优化机制有效平衡了记忆稳定性与学习可塑性。此外，为缓解旧任务带来的冗余神经元问题，引入埃宾浩斯遗忘机制予以释放，从而增强模型提取通用判别特征的能力。实验表明，本方法在等错误率（EER）上相较当前最优持续学习方法RWM提升21.3%。同时，该方法的有效性不仅限于音频伪造检测，在图像识别等任务中也展现出应用潜力。代码已公开于https://github.com/cyjie429/RegO。
原文摘要 · Abstract (English)
Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes when confronted with the diverse and evolving nature of real-world deepfakes. To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection. Specifically, we use the Fisher information matrix to measure important neuron regions for real and fake audio detection, dividing them into four regions. First, we directly fine-tune the less important regions to quickly adapt to new tasks. Next, we apply gradient optimization in parallel for regions important only to real audio detection, and in orthogonal directions for regions important only to fake audio detection. For regions that are important to both, we use sample proportion-based adaptive gradient optimization. This region-adaptive optimization ensures an appropriate trade-off between memory stability and learning plasticity. Additionally, to address the increase of redundant neurons from old tasks, we further introduce the Ebbinghaus forgetting mechanism to release them, thereby promoting the capability of the model to learn more generalized discriminative features. Experimental results show our method achieves a 21.3% improvement in EER over the state-of-the-art continual learning approach RWM for audio deepfake detection. Moreover, the effectiveness of RegO extends beyond the audio deepfake detection domain, showing potential significance in other tasks, such as image recognition. The code is available at https://github.com/cyjie429/RegO
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。