Logo image
Back
Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features
Preprint   Open access

Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features

Lisan Al Amin, Rakib Hossain, Mahbubul Islam, Faisal Quader and Thanh Thi Nguyen
arXiv, Vol.7 May 2026
Cornell University
2026
DOI: https://doi.org/10.48550/arxiv.2605.06035
pdf
2605.06035v1642.51 kBDownloadView
Preprint Version Open Access CC0 V1.0

Abstract

quantum machine learning spectrogram analysis audio deepfake detection anti-spoofing robustness few-shot learning
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.

Details

Metrics

1 Record Views
Logo image