通过稀疏化嵌入层提升语音深度伪造检测的准确率与可解释性。
Sparse deepfake detection promotes better disentanglement
- 在AASIST模型末层嵌入上使用TopK激活生成稀疏表示。
- 在ASVSpoof5测试集上达到23.36%的EER，稀疏度达95%。
- 稀疏表示能更好分离语义特征，部分攻击方式直接编码于潜空间。
由于语音合成技术的快速发展，深度伪造检测已成为语音处理领域的关键挑战。该任务要求系统不仅高效稳健，还需提供可解释的分析。本文聚焦于可解释性中的潜在表征解读，重点关注AASIST模型末层嵌入的表示。我们借鉴稀疏自编码器（SAEs）思想，在该层引入TopK激活机制，生成稀疏表示并用于决策过程。实验表明，稀疏化检测显著提升性能，在ASVSpoof5测试集上实现23.36%的等错误率（EER），同时达到95%的稀疏度。进一步分析显示，这些表示具有更优的解耦能力，通过互信息相关的完整性和模块性指标验证。值得注意的是，部分攻击特征被直接编码于潜空间中。
原文摘要 · Abstract (English)
Due to the rapid progress of speech synthesis, deepfake detection has become a major concern in the speech processing community. Because it is a critical task, systems must not only be efficient and robust, but also provide interpretable explanations. Among the different approaches for explainability, we focus on the interpretation of latent representations. In such paper, we focus on the last layer of embeddings of AASIST, a deepfake detection architecture. We use a TopK activation inspired by SAEs on this layer to obtain sparse representations which are used in the decision process. We demonstrate that sparse deepfake detection can improve detection performance, with an EER of 23.36% on ASVSpoof5 test set, with 95% of sparsity. We then show that these representations provide better disentanglement, using completeness and modularity metrics based on mutual information. Notably, some attacks are directly encoded in the latent space.
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。