Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Machine Intelligence

Applying quantum autoencoders for time series anomaly detection

Robin Frehner, Kurt Stockinger

Published May 5, 2025• 32 citations
Publisher

Abstract

Abstract Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition, or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60–230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts.

DOI
10.1007/s42484-025-00285-1

Related papers

Applying Quantum Autoencoders for Time Series Anomaly Detection

Robin Frehner, Kurt Stockinger

Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60-230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts.

arXiv:2410.04154•Oct 5, 2024•6 citations

Quantum Autoencoders for Anomaly Detection in Cybersecurity

Rohan Senthil, Swee Liang Wong

Abstract Anomaly detection in cybersecurity is a challenging task, where normal events far outnumber anomalous ones with new anomalies occurring frequently. Classical autoencoders have been used for anomaly detection, but struggles in data-limited settings which quantum counterparts can potentially overcome. In this work, we apply Quantum Autoencoders (QAEs) for anomaly detection in cybersecurity, specifically on the BPF-extended tracking honeypot (BETH) dataset. QAEs are evaluated across multiple encoding techniques, ansatz types, repetitions, and feature selection strategies. Our results demonstrate that an 8-feature QAE using Dense-Angle encoding with a RealAmplitude ansatz can outperform Classical Autoencoders (CAEs), even when trained on substantially fewer samples. The effects of quantum encoding and feature selection for developing quantum models are demonstrated and discussed. In a data-limited setting, the best performing QAE model has a F1 score of 0.87, better than that of CAE (0.77). These findings suggest that QAEs may offer practical advantages for anomaly detection in data-limited scenarios.

arXiv:2510.21837•Jul 3, 2026•4 citations

Quantum Convolutional Autoencoders for Reconstruction-Based Anomaly Detection

Donovan Slabbert, Francesco Petruccione

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.

quant-pharXiv:2607.02135•Jul 3, 2026•0 citations

QEA-FAD: Quantum Enhanced Autoencoders for Anomaly Detection in Finance and Healthcare

Sourodeep Kundu, Deepti Mishra, Nachiketa Tarasia +2 more

Quantum Auto-Encoders (QAEs) represent a transformative approach to anomaly detection, leveraging quantum computational power to address challenges in domains such as healthcare and finance. In this study, we focus on detecting anomalies in breast cancer diagnosis and fraudulent financial transactions. QAEs are trained exclusively on non-anomalous data, enabling anomaly detection through their inability to faithfully reconstruct anomalous points. Reconstruction quality is evaluated using fidelity tests for simulations and SWAP tests for quantum hardware, ensuring reliable and robust performance across diverse environments. Our work introduces QEAFAD: Quantum Enhanced Autoencoders for Anomaly Detection, incorporating enhanced and patch-based architectures that demonstrate significant advancements in precision. By integrating quantum entanglement into the encoding and decoding processes, via shared Bell pairs and direct qubit entanglement. Our framework improves correlations and delivers statistically significant performance gains. Benchmarks on the MNIST dataset validate the scalability of our approach, while JAX-accelerated optimization reduces training time on financial datasets. Experiments on IBM and Amazon quantum hardware confirm the practical feasibility of QAEs. These advancements highlight the efficiency of QAEs, achieving superior accuracy with reduced computational resources, making them a compelling solution for real-world anomaly detection challenges in critical applications.

International Conference on Networks and Cryptology (NETCRYPT)•May 29, 2025•3 citations

Quantum Autoencoder for Multivariate Time Series Anomaly Detection

Kilian Tscharke, Maximilian Wendlinger, Afrae Ahouzi +4 more

Anomaly Detection (AD) defines the task of identifying observations or events that deviate from typical - or normal - patterns, a critical capability in IT security for recognizing incidents such as system misconfigurations, malware infections, or cyberattacks. In enterprise environments like SAP HANA Cloud systems, this task often involves monitoring high-dimensional, multivariate time series (MTS) derived from telemetry and log data. With the advent of quantum machine learning offering efficient calculations in high-dimensional latent spaces, many avenues open for dealing with such complex data. One approach is the Quantum Autoencoder (QAE), an emerging and promising method with potential for application in both data compression and AD. However, prior applications of QAEs to time series AD have been restricted to univariate data, limiting their relevance for real-world enterprise systems. In this work, we introduce a novel QAE-based framework designed specifically for MTS AD towards enterprise scale. We theoretically develop and experimentally validate the architecture, demonstrating that our QAE achieves performance competitive with neural-network-based autoencoders while requiring fewer trainable parameters. We evaluate our model on datasets that closely reflect SAP system telemetry and show that the proposed QAE is a viable and efficient alternative for semisupervised AD in real-world enterprise settings.

arXiv:2504.17548•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•11 citations

Assessing the Feasibility of Quantum Autoencoders for Real-World Visual Anomaly Detection

Farida Farsian, Attilio Azzarelli, Fabrizio De Vita +2 more

Quantum Machine Learning (QML) has recently emerged as a promising paradigm for extending classical learning models by leveraging quantum-mechanical properties such as superposition and entanglement. Among the proposed approaches, quantum autoencoders have been introduced as a potential tool for data compression and anomaly detection. However, their applicability to real-world, high-dimensional computer vision tasks remains largely unexplored.In this work, we assess the feasibility of quantum autoencoders for visual anomaly detection using a realistic road-infrastructure dataset characterized by strong class imbalance and fine-grained spatial annotations. We propose a hybrid quantum–classical architecture that combines a classical feature extractor with a variational quantum autoencoder operating on a reduced latent space. The model is designed to process local image patches and detect anomalies based on reconstruction error.We benchmark the proposed approach against a classical autoencoder baseline under the same preprocessing and training conditions. The evaluation considers both reconstruction performance and anomaly detection capability, with particular attention to the challenges posed by sparse and localized anomalies in real-world imagery. The results provide insight into the current capabilities and limitations of quantum autoencoders in practical computer vision settings, highlighting key challenges related to data encoding, model scalability, and integration with classical pipelines.

IEEE International Conference on Smart Computing Workshops and Other Affiliated Events (SMARTCOMP Companion)•Jun 1, 2026•0 citations
Abstract Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition, or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60–230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts.
Anomaly detection is an important problem with applications in various domains such as fraud detection, pattern recognition or medical diagnosis. Several algorithms have been introduced using classical computing approaches. However, using quantum computing for solving anomaly detection problems in time series data is a widely unexplored research field. This paper explores the application of quantum autoencoders to time series anomaly detection. We investigate two primary techniques for classifying anomalies: (1) Analyzing the reconstruction error generated by the quantum autoencoder and (2) latent representation analysis. Our simulated experimental results, conducted across various ansaetze, demonstrate that quantum autoencoders consistently outperform classical deep learning-based autoencoders across multiple datasets. Specifically, quantum autoencoders achieve superior anomaly detection performance while utilizing 60-230 times fewer parameters and requiring five times fewer training iterations. In addition, we implement our quantum encoder on real quantum hardware. Our experimental results demonstrate that quantum autoencoders achieve anomaly detection performance on par with their simulated counterparts.
Abstract Anomaly detection in cybersecurity is a challenging task, where normal events far outnumber anomalous ones with new anomalies occurring frequently. Classical autoencoders have been used for anomaly detection, but struggles in data-limited settings which quantum counterparts can potentially overcome. In this work, we apply Quantum Autoencoders (QAEs) for anomaly detection in cybersecurity, specifically on the BPF-extended tracking honeypot (BETH) dataset. QAEs are evaluated across multiple encoding techniques, ansatz types, repetitions, and feature selection strategies. Our results demonstrate that an 8-feature QAE using Dense-Angle encoding with a RealAmplitude ansatz can outperform Classical Autoencoders (CAEs), even when trained on substantially fewer samples. The effects of quantum encoding and feature selection for developing quantum models are demonstrated and discussed. In a data-limited setting, the best performing QAE model has a F1 score of 0.87, better than that of CAE (0.77). These findings suggest that QAEs may offer practical advantages for anomaly detection in data-limited scenarios.
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 Auto-Encoders (QAEs) represent a transformative approach to anomaly detection, leveraging quantum computational power to address challenges in domains such as healthcare and finance. In this study, we focus on detecting anomalies in breast cancer diagnosis and fraudulent financial transactions. QAEs are trained exclusively on non-anomalous data, enabling anomaly detection through their inability to faithfully reconstruct anomalous points. Reconstruction quality is evaluated using fidelity tests for simulations and SWAP tests for quantum hardware, ensuring reliable and robust performance across diverse environments. Our work introduces QEAFAD: Quantum Enhanced Autoencoders for Anomaly Detection, incorporating enhanced and patch-based architectures that demonstrate significant advancements in precision. By integrating quantum entanglement into the encoding and decoding processes, via shared Bell pairs and direct qubit entanglement. Our framework improves correlations and delivers statistically significant performance gains. Benchmarks on the MNIST dataset validate the scalability of our approach, while JAX-accelerated optimization reduces training time on financial datasets. Experiments on IBM and Amazon quantum hardware confirm the practical feasibility of QAEs. These advancements highlight the efficiency of QAEs, achieving superior accuracy with reduced computational resources, making them a compelling solution for real-world anomaly detection challenges in critical applications.
Anomaly Detection (AD) defines the task of identifying observations or events that deviate from typical - or normal - patterns, a critical capability in IT security for recognizing incidents such as system misconfigurations, malware infections, or cyberattacks. In enterprise environments like SAP HANA Cloud systems, this task often involves monitoring high-dimensional, multivariate time series (MTS) derived from telemetry and log data. With the advent of quantum machine learning offering efficient calculations in high-dimensional latent spaces, many avenues open for dealing with such complex data. One approach is the Quantum Autoencoder (QAE), an emerging and promising method with potential for application in both data compression and AD. However, prior applications of QAEs to time series AD have been restricted to univariate data, limiting their relevance for real-world enterprise systems. In this work, we introduce a novel QAE-based framework designed specifically for MTS AD towards enterprise scale. We theoretically develop and experimentally validate the architecture, demonstrating that our QAE achieves performance competitive with neural-network-based autoencoders while requiring fewer trainable parameters. We evaluate our model on datasets that closely reflect SAP system telemetry and show that the proposed QAE is a viable and efficient alternative for semisupervised AD in real-world enterprise settings.
Quantum Machine Learning (QML) has recently emerged as a promising paradigm for extending classical learning models by leveraging quantum-mechanical properties such as superposition and entanglement. Among the proposed approaches, quantum autoencoders have been introduced as a potential tool for data compression and anomaly detection. However, their applicability to real-world, high-dimensional computer vision tasks remains largely unexplored.In this work, we assess the feasibility of quantum autoencoders for visual anomaly detection using a realistic road-infrastructure dataset characterized by strong class imbalance and fine-grained spatial annotations. We propose a hybrid quantum–classical architecture that combines a classical feature extractor with a variational quantum autoencoder operating on a reduced latent space. The model is designed to process local image patches and detect anomalies based on reconstruction error.We benchmark the proposed approach against a classical autoencoder baseline under the same preprocessing and training conditions. The evaluation considers both reconstruction performance and anomaly detection capability, with particular attention to the challenges posed by sparse and localized anomalies in real-world imagery. The results provide insight into the current capabilities and limitations of quantum autoencoders in practical computer vision settings, highlighting key challenges related to data encoding, model scalability, and integration with classical pipelines.