使用交叉注意力特征融合的半真音频深度伪造检测与定位
Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Study
AI总结：
提出CAFNet模型，通过三元分类和边界回归联合检测部分伪造音频，在MLADDC数据集上达到92.71%准确率和0.075s定位误差。
摘要：
音频深度伪造检测通常作为二分类问题研究，但部分篡改语音（其中一段短合成片段被拼接进真实语音）构成了更困难且更现实的威胁。检测此类半真音频不仅需要区分真实和完全伪造语音，还需要定位篡改发生的位置。我们提出了CAFNet，一个576k参数的架构，联合处理这两个任务：它在单次前向传播中执行三元分类（真实、完全伪造或半真）并回归合成区域的时间边界。CAFNet通过并行深度可分离卷积分支和交叉注意力融合梅尔频率倒谱系数（MFCC）、线性频率倒谱系数（LFCC）和色度短时傅里叶变换（Chroma-STFT）特征，随后使用双向长短期记忆（BiLSTM）回归头进行边界预测。在组合的多语言音频深度伪造检测语料库（MLADDC）T2+T3测试集上，CAFNet达到92.71%的准确率和0.9910的宏观曲线下面积（AUC），边界定位平均绝对误差（MAE）为0.075秒，中位误差为0.052秒。在二分类检测中，它达到96.76%的准确率和3.20%的等错误率（EER），以超过500倍的参数减少优于微调的XLS-R 300M（78.31%）和AST 87M（93.03%）。跨数据集研究进一步表明，即使在降低骨干学习率的情况下，标准微调也会破坏跨域表示。
英文摘要：
Partially manipulated (half-truth) speech, where a short synthesised segment is spliced into an otherwise genuine utterance, is a harder and more realistic forensic threat than the fully synthesised deepfakes that dominate the literature. We present CAFNet, a lightweight (576K-parameter, 2.24 MB) cross-attentive architecture that fuses MFCC, LFCC, and Chroma-STFT features to jointly classify audio as real, fully fake, or half-truth, and regress the temporal boundaries of the synthesised region, at approximately 14 ms CPU latency. A component ablation shows cross-attention fusion is CAFNet's most load-bearing component; a deeply supervised auxiliary classification head from earlier iterations is not, and removing it improves every in-domain metric under 3-seed replication with substantially lower variance. On MLADDC T2+T3 the model reaches 97.55%$\pm$0.69% ternary accuracy and 0.037 s boundary mean absolute error (MAE), to our knowledge, the first reported continuous splice- boundary localisation result on this benchmark. Zero-shot evaluation on two independent benchmarks shows transfer is capability- and corpus-dependent rather than uniform: on Half-Truth Audio Detection dataset (HAD), detection recall reaches 84.9% and ternary classification resolves half-truth correctly on half of true half-truth clips (50.4%), while on PartialSpoof, binary detection stays near chance (AUC 0.5544). We treat this asymmetry, not a single generalization verdict, as the finding. HAD localisation improves in absolute terms but degrades in relative terms, since in-domain localisation improved faster. An architectural change validated purely in-domain thus shifted the cross-corpus transfer profile, evidence that cross-corpus evaluation should accompany, not follow, in-domain architecture decisions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
