解决音频伪造中真假混杂的检测难题，精准定位伪造片段。
ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection
- 用大模型动态调度工具，分步分析音频真伪
- 在混合真实性数据上提升3.72~14.39点宏F1
- 可解释性强，定位到具体时间与声源
音频深度伪造检测通常被建模为单领域音频的片段级二分类任务。然而，现实中的伪造音频可能呈现混合真实性，即真实与伪造线索在时间过渡、声源重叠或两者兼有情况下共存。该场景不仅要求识别伪造音频，还需定位提供判断依据的成分。我们提出ToolDF，一种面向混合真实性音频伪造检测的工具集成推理框架。ToolDF采用音频大语言模型作为调度器，通过监督式工具使用轨迹进行训练。它能自适应分析音频场景，选择性执行声源分离，将各成分路由至领域专用专家，并聚合证据生成可解释的判断结果。我们进一步构建了涵盖时间过渡、声学重叠和混合混合的混合真实性ADD基准。实验表明，ToolDF在复合型检测任务中表现最佳，相比最强单体基线和固定流水线分别实现3.72和14.39点的宏F1提升，同时提供可解释的证据，定位至时间区域与声源。源代码与数据集已公开。
原文摘要 · Abstract (English)
Audio deepfake detection is commonly formulated as clip-level binary classification of single-domain audio. However, real-world manipulated audio can exhibit mixed authenticity, where genuine and manipulated cues coexist across temporal transitions, overlapping sources, or both. This setting requires not only detecting manipulated audio but also localizing the components that provide evidence for the decision. We propose ToolDF, a tool-integrated reasoning framework for mixed-authenticity audio deepfake detection. ToolDF employs an audio large language model as an orchestrator trained with supervised tool-use trajectories. It adaptively analyzes the audio scene, selectively performs source separation, routes components to domain-specific experts, and aggregates their evidence into an interpretable verdict. We further introduce a mixed-authenticity ADD benchmark covering temporal transitions, acoustic overlaps, and hybrid mixtures. Experimental results show that ToolDF achieves the best overall performance on composite-type detection, achieving macro-F1 gains of 3.72 and 14.39 points over the strongest monolithic baseline and a fixed pipeline, respectively, while providing interpretable evidence localized to temporal regions and acoustic sources. Our source code and dataset are publicly available online.
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。