做语音安全或深度伪造检测的开发者，这篇论文能帮你理解不同模型的实际决策逻辑，避免盲目调参——看完你会知道该关注环境音还是音素质感。
这篇论文提出了一种基于集成梯度的音频可解释性方法，用于分析深度伪造语音检测器的决策依据。研究者对三种基于WavLM的检测器（AASIST、CA-MHFA、SLS）在ASVspoof 5数据集上进行分析，发现尽管性能相近，它们依赖的线索截然不同：AASIST更关注非语音/环境线索，CA-MHFA聚焦于局部音素伪影，而SLS则依赖词边界和频谱完整性。通过因果掩码验证，研究者证实了这些线索对检测性能的关键影响。这项工作揭示了深度伪造检测的“黑箱”问题，为改进检测器的鲁棒性和可解释性提供了方向。
What Do Deepfake Speech Detectors Actually Hear?
Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision. We propose an audio-native explainability pipeline using Integrated Gradients on time-aligned self-supervised representations to localize decision evidence over time. We apply the proposed method to three WavLM-based detectors (AASIST, CA-MHFA, SLS) on ASVspoof 5 and manually annotate the highest-attribution regions to provide a semantic meaning of the most important cues. Despite similar performance, the detectors rely on different cues: AASIST emphasizes non-speech/environment cues, CA-MHFA focuses on localized phoneme artifacts, and SLS relies on word boundaries and spectral integrity. We move beyond speculative reasoning and validate our findings by causal masking of the primary detector cues. Observed performance degradation further supports the explained detector semantics.