Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features

TL;DR

This paper introduces Q-Patch, a quantum feature map for audio spectrograms, improving deepfake detection by leveraging time-frequency structures with practical quantum circuits.

Contribution

Q-Patch is a novel quantum kernel method that encodes local spectrogram patches into quantum states, enhancing audio deepfake detection in near-term quantum devices.

Findings

Q-Patch achieves an AUROC of 0.87 in audio spoofing detection.

It outperforms classical RBF-SVM baseline with AUROC of 0.82.

Kernel analysis shows clear class separation and similarity metrics.

Abstract

Quantum machine learning has emerged as a promising tool for pattern recognition, yet many audio-focused approaches still treat spectrograms as generic images and do not explicitly exploit their time-frequency structure. We propose Q-Patch, a quantum feature map tailored to audio that encodes local time-frequency patches from mel-spectrograms into quantum states using shallow, hardware-efficient circuits with adjacency-aware entanglement. Each selected patch is summarized by a compact four-dimensional acoustic descriptor and mapped to a four-qubit circuit with depth at most three, enabling practical quantum kernel construction under near-term constraints. We evaluate Q-Patch on an audio spoofing detection task using a controlled, balanced protocol and compare it with size-matched classical baselines. Q-Patch improves discrimination between bona fide and spoofed samples, achieving an area under the receiver operating characteristic curve (AUROC) of 0.87, compared with 0.82 for a radial basis function support vector machine (RBF-SVM) trained on the same patch-level features. Kernel-space analysis further reveals a clear class structure, with cross-class similarity around 0.615 and within-class self-similarity of 1.00. Overall, Q-Patch provides a practical framework for incorporating time-frequency-aware representations into quantum kernel learning for audio authenticity assessment in low-resource settings.