A Fourier Explanation of AI-music Artifacts

2025-06-23

AI Summary

This work addresses the challenge of detecting AI-generated music by identifying a systematic spectral artifact—interpretable high-frequency harmonic peaks—introduced by deconvolution modules. These artifacts share a common origin with checkerboard artifacts and stem from intrinsic architectural flaws in generative models, rather than data biases. Methodologically, the study integrates Fourier analysis, spectral modeling, and rigorous mathematical proof to demonstrate the universality of this phenomenon across commercial models (e.g., Suno, Udio) and open-source architectures. The core contribution is a lightweight, interpretable detection criterion: identifying anomalous harmonic peaks within specific frequency bands. This criterion achieves >99% accuracy across diverse scenarios, matching the performance of complex deep learning detectors. It constitutes the first theory-driven, architecture-defect-based solution for AI audio forensics.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rapid rise of generative AI has transformed music creation, with millions of users engaging in AI-generated music. Despite its popularity, concerns regarding copyright infringement, job displacement, and ethical implications have led to growing scrutiny and legal challenges. In parallel, AI-detection services have emerged, yet these systems remain largely opaque and privately controlled, mirroring the very issues they aim to address. This paper explores the fundamental properties of synthetic content and how it can be detected. Specifically, we analyze deconvolution modules commonly used in generative models and mathematically prove that their outputs exhibit systematic frequency artifacts -- manifesting as small yet distinctive spectral peaks. This phenomenon, related to the well-known checkerboard artifact, is shown to be inherent to a chosen model architecture rather than a consequence of training data or model weights. We validate our theoretical findings through extensive experiments on open-source models, as well as commercial AI-music generators such as Suno and Udio. We use these insights to propose a simple and interpretable detection criterion for AI-generated music. Despite its simplicity, our method achieves detection accuracy on par with deep learning-based approaches, surpassing 99% accuracy on several scenarios.

Problem

• Detect AI-generated music via frequency artifacts
• Analyze deconvolution modules in generative models
• Propose interpretable detection for synthetic content

Innovation

• Analyzes frequency artifacts in AI-music outputs
• Proves artifacts inherent to model architecture
• Proposes simple interpretable detection criterion