A central goal of quantum machine learning is to identify applications in which small quantum circuits can improve task performance while remaining executable on real hardware. We investigate deepfake (synthetic) speech detection, a largely unexplored application in this area, where reliable confidence scores are as important as discrimination performance because deployment decisions are made at fixed thresholds and overconfident errors can be costly. We introduce QBFF, which routes a compressed speech representation through a small 8-qubit variational circuit (VQC) used as a drop-in bottleneck, with a matched classical bottleneck as the control. The quantum circuit yields better-calibrated confidence in most matched comparisons, including out-of-distribution evaluation, though the downstream deployment-cost benefit is model-dependent. We then run the same circuit on a real IBM quantum processor. To our knowledge, this is the first anti-spoofing pipeline to run on a QPU; hardware execution demonstrates feasibility, with lower subset EER and $C_{llr}$ but higher mean actDCF than the matched classical reference. Together, these results show that hardware-executable quantum bottlenecks can improve score reliability, with gains that vary by evaluation setting.
AI Summary
The paper asks whether a small variational quantum circuit used inside a classical speech anti-spoofing pipeline can improve discrimination and confidence calibration. QBFF compresses a 1024-dimensional XLS-R speech embedding to 16 bounded inputs, processes them with an eight-qubit, two-layer data-reuploading circuit containing 48 trainable parameters, and feeds eight Pauli-$Z$ expectations through learned scaling and a classifier. Comparisons use a classical bottleneck matched in interface dimensions and nominal depth, with three training seeds across pooling choices, frozen and fine-tuned encoders, and in-domain and out-of-domain datasets.
Results depend on the setting. With fine-tuning and augmentation, AASIST+QBFF reduces In-the-Wild EER from $5.49\%$ to $3.97\%$ versus the classical bottleneck, and actDCF from $0.205$ to $0.181$. Frozen-encoder experiments show mixed discrimination changes but lower actDCF for both attentive poolings on both datasets. Raw calibration error also decreases; however, post-hoc calibration gives the classical bottleneck lower best ECE, and quantum improvements do not consistently extend to Dev-tuned deployment cost or mean pooling.
Hardware inference on IBM processors establishes executability on a hardness-stratified subset, not full-benchmark performance. Five 512-shot runs yield mean EER $4.7\%$ versus $7.29\%$ classically, but actDCF worsens from $0.227$ to $0.62$ with substantial variability. Mitigation settings were not independently verified. The paper also identifies the need for a bounded-output classical control to isolate measurement-bound effects; learned output scaling means bounded quantum expectations alone do not guarantee calibration.
Little sign of AI-generated textIncrementalMissing comparison
Error found: The frozen-MHFA In-the-Wild results report EER of 11.98±1.74% and C_llr of 0.359±0.615 over three seeds, which cannot simultaneously satisfy the stated C_llr definition, undermining a repeatedly highlighted reliability result.
Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.
Comments
Accepted for publication at the 2026 IEEE 2nd International Conference on Quantum Artificial Intelligence (QAI)
A central goal of quantum machine learning is to identify applications in which small quantum circuits can improve task performance while remaining executable on real hardware. We investigate deepfake (synthetic) speech detection, a largely unexplored application in this area, where reliable confidence scores are as important as discrimination performance because deployment decisions are made at fixed thresholds and overconfident errors can be costly. We introduce QBFF, which routes a compressed speech representation through a small 8-qubit variational circuit (VQC) used as a drop-in bottleneck, with a matched classical bottleneck as the control. The quantum circuit yields better-calibrated confidence in most matched comparisons, including out-of-distribution evaluation, though the downstream deployment-cost benefit is model-dependent. We then run the same circuit on a real IBM quantum processor. To our knowledge, this is the first anti-spoofing pipeline to run on a QPU; hardware execution demonstrates feasibility, with lower subset EER and Cllr but higher mean actDCF than the matched classical reference. Together, these results show that hardware-executable quantum bottlenecks can improve score reliability, with gains that vary by evaluation setting.
The paper asks whether a small variational quantum circuit used inside a classical speech anti-spoofing pipeline can improve discrimination and confidence calibration. QBFF compresses a 1024-dimensional XLS-R speech embedding to 16 bounded inputs, processes them with an eight-qubit, two-layer data-reuploading circuit containing 48 trainable parameters, and feeds eight Pauli-Z expectations through learned scaling and a classifier. Comparisons use a classical bottleneck matched in interface dimensions and nominal depth, with three training seeds across pooling choices, frozen and fine-tuned encoders, and in-domain and out-of-domain datasets.
Results depend on the setting. With fine-tuning and augmentation, AASIST+QBFF reduces In-the-Wild EER from 5.49% to 3.97% versus the classical bottleneck, and actDCF from 0.205 to 0.181. Frozen-encoder experiments show mixed discrimination changes but lower actDCF for both attentive poolings on both datasets. Raw calibration error also decreases; however, post-hoc calibration gives the classical bottleneck lower best ECE, and quantum improvements do not consistently extend to Dev-tuned deployment cost or mean pooling.
Hardware inference on IBM processors establishes executability on a hardness-stratified subset, not full-benchmark performance. Five 512-shot runs yield mean EER 4.7% versus 7.29% classically, but actDCF worsens from 0.227 to 0.62 with substantial variability. Mitigation settings were not independently verified. The paper also identifies the need for a bounded-output classical control to isolate measurement-bound effects; learned output scaling means bounded quantum expectations alone do not guarantee calibration.
Under tight feature and compute budgets, classical threat detection pipelines often degrade on near-decision-boundary events. Small quantum processors are now available, but existing work inadequately shows whether quantum components improve end-to-end threat detection under the above resource constrained conditions. This paper tries to address this gap with a hybrid architecture that uses a compact multilayer perceptron layer to compress the information in data and then routes the processed features to a few qubit quantum heads implemented in quantum support vector machine (QSVM) and variational quantum circuit (VQC) models. On a simulation platform, we benchmark these hybrid models against classical models with comparable parameter budgets on two representative cybersecurity tasks, network intrusion detection on NSL-KDD dataset and spam filtering on Ling-Spam dataset. To validate their precision on real quantum hardware, we deploy the best 4-qubit QSVM model on an IBM Quantum device with noise-aware execution, evaluated on a smaller sub-dataset. In the results, shallow quantum heads consistently match, and on difficult near-boundary cases modestly reduce missed attacks and false alarms compared to classical models using the same features. Hardware validation results track the simulation behavior closely enough that the remaining gap is dominated by device noise rather than model design. Furthermore, we conduct adversarial attacks to test the robustness of one QSVM model. Taken together, the study shows that even on small, noisy devices, carefully engineered quantum components may function as competitive, budget-aware components in practical cyber threat detection applications.
Abstract A recurring weakness in quantum machine learning (QML) is that reported ‘quantum advantages’ are seldom tested against a capacity-matched classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly—a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does not help, and validation on real quantum hardware—which we develop and apply through a concrete case study. That case study is Quantum Adaptive Self-Attention (QASA), a hybrid Transformer that replaces the value projection of a single encoder layer with a 36-parameter parameterized quantum circuit (PQC), keeping all other layers classical. Across nine synthetic benchmarks and the real-world ETTh1 dataset, QASA improves on a full-capacity classical Transformer for chaotic and trend-dominated signals. To ask whether this is a genuinely quantum effect, we introduce a control rarely applied in QML—a capacity-matched classical bottleneck with the same parameter budget—and find that it matches the PQC on the error metrics. The gain is therefore attributable to the low-rank value-projection bottleneck (an architectural parsimony principle), not to quantumness; adding further quantum layers only degrades performance and trainability. We accordingly position the quantum layer not as a source of accuracy advantage but as a competitive instantiation of this principle: its low-rank compression onto the signal’s intrinsic dimensionality is matched by a classical bottleneck, so the gain is architectural rather than quantum. The quantum layer’s distinguishing features are physical—a high circuit entanglement (Meyer–Wallach Q = 0.981 with only 27 CNOTs, which we report as a circuit-level property) and, most concretely, noisy intermediate-scale quantum deployability, which we verify by executing the trained model on a real IBM Quantum processor (one-step prediction within 7.5 % of noiseless simulation on the quantum-favored task and 25 % , with overlapping error bars, on a classical-favored control; no error mitigation). Relative to other quantum sequence models (quantum long short-term memory (QLSTM), QnnFormer), QASA is moreover the most resource-efficient of the three: it reaches competitive accuracy with the fewest quantum parameters (36 vs 90–128) and the strongest entanglement-per-gate ( Q = 0.981 with 27 CNOTs vs QLSTM’s 56), and retains trainable gradients that deeper circuits lose. We argue that capacity-matched baselines and honest reporting of where quantum does not help are prerequisites for credible quantum-machine-learning claims.
In this paper, we introduce a quantum kernel-based method to classify deepfake audio using manually extracted acoustic features. Each audio sample is represented by a 194-dimension feature vector. Features are scaled using training-set statistics and compressed to 8 principal components through PCA, then normalized into the range [−π,π] in order to perform the angle encoding on quantum circuits. Then, we present a quantum feature map with 8-qubits based on IQP-inspired architecture including Hadamard gates, RZ(xi) rotation and neighboring Ising-ZZ interaction. The quantum kernel is evaluated by the probability of all-zero state when Uϕ(xi) is applied, followed by Uϕ†(xj). We employ the quantum kernel matrix in the SVM classifier to perform real and fake audio detection. For comparison, a classic RBF-SVM and a Hybrid Variational Quantum Classifier trained with the same preprocessed feature representation are evaluated. The experiments were performed on the FoR-2Sec dataset show that QKSVM achieves an accuracy of 0.9894 in accuracy, F1-score of 0.9894, ROC-AUC of 0.9992, EER of 0.0101, and MCC of 0.9788. The McNemar’s test performed on QKSVM and classic RBF-SVM gives b=41,c=14,χ2=12.2909,p=0.000455. This means that the two classifiers have a statistically significant difference at 0.05 level. The results suggest that quantum kernel-based similarity learning can provide a competitive classification approach for deepfake audio detection using compact acoustic representations.
The development of quantum machine learning demonstrates its quantum advantages over traditional deep learning, which promises to discover new patterns on supervised classification datasets. This work proposes a classical-to-quantum transfer learning system based on the large-scale unsupervised pre-trained model to demonstrate the competitive performance of quantum transfer learning for synthetic speech detection. We use the pre-trained model WavLM-Large to extract feature maps from speech signals, obtain low-dimensional embedding vectors through classical network components, and then jointly fine-tune the pre-trained model and classical network components with a variational quantum circuit (VQC). We evaluate our system on the ASVspoof 2021 DF task, and the experiments using quantum circuit simulations show that quantum transfer learning can improve the performance of the classical transfer learning baseline on the task.
Quantum convolutional neural networks (QCNNs) have become increasingly popular in quantum machine learning (QML) due to their efficient parameterization and hierarchical representation of quantum information. Anomaly detection is an important machine learning task with applications across a wide range of domains, including scientific data analysis. In this work, we adapt a QCNN architecture into a quantum autoencoder (QAE) framework for reconstruction-based anomaly detection. The models are trained in a semi-supervised manner on normal samples to reconstruct feature-extracted and dimensionally reduced time-series data, with reconstruction error used as an anomaly score. We investigate two quantum convolutional autoencoder architectures that differ in their treatment of latent information: a hierarchical architecture in which information remains distributed across the circuit and a bottleneck-based architecture in which information is explicitly compressed and reconstructed using additional decoder qubits. The size of the quantum latent space is varied to study its influence on reconstruction accuracy and anomaly detection performance. The approaches are benchmarked against both a variational quantum circuit and a comparable classical baseline using a real-world exoplanet anomaly-detection dataset. Results indicate a trade-off between latent-space size and model capacity, while also suggesting that explicit latent-space compression through a quantum bottleneck can improve anomaly detection performance relative to architectures that retain information throughout the circuit.
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.
Muhammad Shafique