GLAD：用于鲁棒语音深度伪造检测的全局-局部自适应检测器
GLAD: Global-Local Adaptive Detector for Robust Speech Deepfake Detection
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出GLAD全局-局部自适应检测器，通过分层全局-局部骨干网络捕获局部伪造痕迹，引入分层自适应门控机制应对层重要性变化，并采用SaniBoost数据增强策略，显著提升语音深度伪造检测在未见领域的鲁棒性。
AI中文摘要：
近年来，基于人工智能的语音合成技术取得了显著进展，能够生成高度逼真的语音，这使得语音深度伪造检测（SDD）在防止滥用方面的重要性日益增加。虽然主流的基于自监督学习（SSL）的检测器取得了强劲的性能，但它们对未见领域的泛化能力较差，并且由于偏向全局语义一致性，常常忽略细粒度的信号伪影。在本文中，我们首次进行了详细的实证和可视化分析，以明确验证这些局限性。我们的调查揭示了两个关键的架构脆弱性：（1）系统性地无法捕获局部伪造痕迹，以及（2）严重缺乏对SSL层重要性领域驱动变化的适应性，导致静态聚合策略容易过拟合。为了解决这些脆弱性，我们提出了全局-局部自适应检测器（GLAD）。具体而言，为了捕获局部伪造，GLAD采用了一种分层全局-局部（HGL）骨干网络，通过融合全局语言和声学特征与细粒度的局部信号细节，明确弥合了粒度差距。为了应对分布外（OOD）场景中的层重要性变化，我们引入了一种分层自适应门控（HAG）机制，该机制以样本特定的方式动态重新校准层级关注。最后，为了解决环境偏差引起的捷径学习问题，我们引入了SaniBoost，一种复合数据增强策略，用于稳健的信号标准化和噪声净化。大量实验表明，GLAD显著优于最先进的方法，尤其是在未见领域上。代码将在发表后发布。
英文摘要：
Recent advances in AI-based speech synthesis have enabled highly realistic speech, increasing the importance of speech deepfake detection (SDD) in preventing misuse. While mainstream Self-Supervised Learning (SSL)-based detectors achieve strong performance, they suffer from poor generalization to unseen domains and often overlook fine-grained signal artifacts due to a bias towards global semantic consistency. In this paper, we conduct the first detailed empirical and visual analysis to validate these limitations explicitly. Our investigation reveals two critical architectural vulnerabilities: (1) a systemic failure to capture localized spoofing traces, and (2) a severe lack of adaptability to domain-driven shifts in SSL layer importance, rendering static aggregation strategies prone to overfitting. To address these vulnerabilities, we propose the Global-Local Adaptive Detector (GLAD). Specifically, to capture localized forgeries, GLAD employs a Hierarchical Global-Local (HGL) backbone that explicitly bridges the granularity gap by fusing global linguistic and acoustic features with fine-grained local signal details. To counter layer importance shifts in out-of-distribution (OOD) scenarios, we introduce a Hierarchical Adaptive Gating (HAG) mechanism that dynamically recalibrates layer-wise focus in a sample-specific manner. Finally, to address shortcut learning induced by environmental biases, we introduce SaniBoost, a composite data augmentation strategy for robust signal standardization and noise sanitization. Extensive experiments demonstrate that GLAD significantly outperforms state-of-the-art methods, particularly on unseen domain cases.The code will be released upon publication.
