MusicDET: Zero-Shot AI-Generated Music Detection

Detecting AI-generated music is crucial for preserving artistic authenticity and preventing the misuse of generative music technologies. However, existing discriminative detectors typically rely on generated samples during training and often suffer from severe performance degradation when confronted with music produced by unseen generators, which limits their real-world applicability. To address this issue, we formulate a zero-shot setting for AI-generated music detection, where the detector is trained exclusively on real music without access to any generated samples. Under this setting, we propose MusicDET, a generator-agnostic detection framework based on frequency-guided normalizing flows that probabilistically models the distribution of real music features. By evaluating the likelihood of an input sample under the learned real-music distribution, MusicDET enables effective detection of out-of-distribution music signals. Experiments on the FakeMusicCaps and SONICS datasets show that MusicDET consistently outperforms conventional discriminative detectors, particularly when detecting music generated by previously unseen models. The code is at https://github.com/Chaolei98/MusicDET

AI generated music becomes increasingly common, but it is hard to tell apart from real compositions, which risks undermining artistic authenticity. Existing detection methods often fail when they encounter music from new AI generators because they rely on examples of generated music during training. We develop MusicDET, a tool that learns only from real music. It models the natural patterns in real compositions, such as harmonics, energy distribution, and temporal structure, so that music deviating from these patterns is identified as AI generated. Tests on multiple datasets show that MusicDET reliably detects AI generated music, even from generators it never sees before. This approach helps protect musicians’ work, ensures trustworthy music content, and provides a general purpose method for identifying AI created audio.