通过提取音频编码器残留物，用物理取证法高效识别AI生成音乐。
ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics
- 从频谱中提取编码器残留特征，用7通道物理指纹分类
- 在6183首曲目上测试，F1达0.9829，误报率仅1.49%
- 模型轻量且跨编码格式鲁棒，适合实际部署
我们提出ArtifactNet，一种轻量级框架，将AI生成音乐检测重构为物理取证问题——直接提取神经音频编码器在生成音频中留下的物理痕迹。采用参数量360万的有界掩码UNet（ArtifactUNet）从幅度谱图中提取编码器残差，并通过HPSS分解为7通道取证特征，再由0.4百万参数的紧凑CNN（总参数400万）进行分类。我们构建了ArtifactBench多生成器评估基准，包含6183首曲目（4383首来自22个生成器的AI音乐，1800首真实音乐，来源6类），每首曲目均标注bench_origin以支持零样本评估。在未见测试集（n=2263）上，ArtifactNet达到F1=0.9829，FPR=1.49%，显著优于CLAM（F1=0.7576，FPR=69.26%）和SpecTTTra（F1=0.7713，FPR=19.43%），所有对比均使用公开检查点、相同条件。采用编码器感知训练（四类格式WAV/MP3/AAC/Opus增强）使跨编码格式概率漂移降低83%（Delta从0.95降至0.16），解决了主要的编码格式不变性失效问题。结果表明，直接提取编码层痕迹的物理取证方法，相比表征学习更具泛化能力与参数效率，参数量仅为CLAM的1/49，SpecTTTra的1/4.8。
原文摘要 · Abstract (English)
We present ArtifactNet, a lightweight framework that detects AI-generated music by reframing the problem as forensic physics -- extracting and analyzing the physical artifacts that neural audio codecs inevitably imprint on generated audio. A bounded-mask UNet (ArtifactUNet, 3.6M parameters) extracts codec residuals from magnitude spectrograms, which are then decomposed via HPSS into 7-channel forensic features for classification by a compact CNN (0.4M parameters; 4.0M total). We introduce ArtifactBench, a multi-generator evaluation benchmark comprising 6,183 tracks (4,383 AI from 22 generators and 1,800 real from 6 diverse sources). Each track is tagged with bench_origin for fair zero-shot evaluation. On the unseen test partition (n=2,263), ArtifactNet achieves F1 = 0.9829 with FPR = 1.49%, compared to CLAM (F1 = 0.7576, FPR = 69.26%) and SpecTTTra (F1 = 0.7713, FPR = 19.43%) evaluated under identical conditions with published checkpoints. Codec-aware training (4-way WAV/MP3/AAC/Opus augmentation) further reduces cross-codec probability drift by 83% (Delta = 0.95 -> 0.16), resolving the primary codec-invariance failure mode. These results establish forensic physics -- direct extraction of codec-level artifacts -- as a more generalizable and parameter-efficient paradigm for AI music detection than representation learning, using 49x fewer parameters than CLAM and 4.8x fewer than SpecTTTra.
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。