用辅助标签选样，提升音频伪造检测的持续学习能力
Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection
- 用生成辅助标签指导记忆样本选择，增强多样性
- 在五次连续任务中平均误报率仅1.953%
- 适合需要持续更新的音频伪造检测系统
现有音频伪造检测框架在面对新型攻击时性能下降。基于回放的持续学习（CL）通过使用少量旧数据更新模型，可在保留旧知识的同时融入新信息。但现有回放技术未能有效捕捉音频特征的多样性，导致偏差并增加遗忘风险。为此，我们提出辅助信息引导采样回放（RAIS），一种面向音频伪造检测的回放式持续学习方法。RAIS采用标签生成网络生成辅助标签，指导记忆缓冲区中多样化样本的选择。大量实验表明，RAIS优于现有最先进方法，在五次连续任务中平均等错误率（EER）达1.953%。代码已公开：https://github.com/falihgoz/RAIS。
原文摘要 · Abstract (English)
The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning (CL), which updates models using a limited set of old data samples, helps preserve prior knowledge while incorporating new information. However, existing rehearsal techniques don't effectively capture the diversity of audio characteristics, introducing bias and increasing the risk of forgetting. To address this challenge, we propose Rehearsal with Auxiliary-Informed Sampling (RAIS), a rehearsal-based CL approach for audio deepfake detection. RAIS employs a label generation network to produce auxiliary labels, guiding diverse sample selection for the memory buffer. Extensive experiments show RAIS outperforms state-of-the-art methods, achieving an average Equal Error Rate (EER) of 1.953 % across five experiences. The code is available at: https://github.com/falihgoz/RAIS.
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。