Implementing efficient machine learning (ML) is extremely difficult for Internet of Things (IoT) devices with limited computational power, memory, and energy resources. We introduce TinyQL, a quantum machine learning framework for Internet of Things (IoT) devices with limited resources. The framework tackles three main issues: dimensionality reduction using variational quantum circuits while maintaining anomaly detection capabilities; model compression using entropy-based structured pruning and parameter quantization; and effective encoding of classical network traffic data into quantum states using amplitude embedding. TinyQL can be deployed on devices with limited quantum simulation capabilities by combining a quantum autoencoder with traditional optimization approaches. The CICIDS 2017 intrusion detection dataset is used to assess the framework, and it is contrasted with traditional autoencoder methods. According to experimental data, TinyQL requires substantially fewer parameters and has a smaller memory footprint than classical approaches without degradation of detection accuracy. Deployment on resource-constrained IoT devices is made possible by the optimized models’ $\mathbf{9 8. 0 8 \%}$ detection accuracy and up to 93.75% memory savings when compared to the original quantum model. An entropy-based pruning strategy tailored for quantum circuits, a novel quantum autoencoder architecture optimized for IoT constraints, a thorough evaluation framework contrasting quantum and classical approaches for IoT anomaly detection, and useful recommendations for implementing quantum machine learning models on edge devices are among the contributions.
Implementing efficient machine learning (ML) is extremely difficult for Internet of Things (IoT) devices with limited computational power, memory, and energy resources. We introduce TinyQL, a quantum machine learning framework for Internet of Things (IoT) devices with limited resources. The framework tackles three main issues: dimensionality reduction using variational quantum circuits while maintaining anomaly detection capabilities; model compression using entropy-based structured pruning and parameter quantization; and effective encoding of classical network traffic data into quantum states using amplitude embedding. TinyQL can be deployed on devices with limited quantum simulation capabilities by combining a quantum autoencoder with traditional optimization approaches. The CICIDS 2017 intrusion detection dataset is used to assess the framework, and it is contrasted with traditional autoencoder methods. According to experimental data, TinyQL requires substantially fewer parameters and has a smaller memory footprint than classical approaches without degradation of detection accuracy. Deployment on resource-constrained IoT devices is made possible by the optimized models’ 98.08% detection accuracy and up to 93.75% memory savings when compared to the original quantum model. An entropy-based pruning strategy tailored for quantum circuits, a novel quantum autoencoder architecture optimized for IoT constraints, a thorough evaluation framework contrasting quantum and classical approaches for IoT anomaly detection, and useful recommendations for implementing quantum machine learning models on edge devices are among the contributions.
The blistering development of the Internet of Things (IoT) has brought an urgent necessity to an efficient data processing at the end of the network, where devices are characterized by few computational capabilities, and little to no energy availability. Conventional machine learning (ML) solutions can offer high-performance on a centralized system, but do not provide the edge environments with the required latency and the corresponding performance. This paper gives a quantum machine learning (QML)-backed architecture that is used to optimize IoT edge processing, inspiring quantum feature encoding along with quantum neural networks with classical post-processing resource allocation. Different simulated IoT datasets were tested on the framework and they all represent applications to smart home, industrial IoT, and environment monitoring. According to experimental findings, processing latency (improved by 39 percent), energy consumption (improved by 40 percent), memory reorganization (improved by 40 percent), and prediction accuracy (improved by 6 per cent.) were significantly less than conventional ML models. The results demonstrate that QML models are able to make real-time decisions significant and scalable as well as sustainable in edge computing. Quantum-enhanced edge intelligence can significantly improve IoT data processing speed, efficiency, and smart decision-making.
The growing complexity of Internet of Things (IoT) networks has generated massive multivariate time-series data at the edge, challenging traditional forecasting and anomaly-detection models due to limited computation, memory, and energy on edge devices. Quantum machine learning (QML) provides a promising solution through expressive, parameter-efficient models that align with these constraints. This study proposes two distinct quantum-classical approaches for edge-based IoT analytics. The first combines a Quantum Neural Network (QNN) with a Quantum Autoencoder (QAE) to deliver lightweight forecasting and anomaly detection. The second employs Quantum Long Short-Term Memory (QLSTM) networks, exploring multiple variants and introducing optimization strategies to enable efficient deployment on a Raspberry Pi 5 using PennyLane simulators. Both approaches are evaluated on two real-world IoT datasets Bker (weather parameters) and ETTm1 (transformer temperature) and with a unified preprocessing pipeline incorporating normalization and PCA-based dimensionality reduction. Results show that QLSTM variants achieve superior forecasting accuracy, while QNN+QAE ensures robust anomaly detection with minimal resource overhead. A lightweight QLSTM variant strikes the best balance between accuracy and inference latency, enabling real-time edge deployment. To our knowledge, this is among the first practical demonstrations of QML-based forecasting and anomaly detection directly on edge hardware, highlighting a feasible pathway toward quantum-enhanced IoT intelligence.
With the growth of Internet of Things (IoT)-based devices, there has been a proliferation of high-dimensional data streams that can be very difficult to handle using traditional machine learning methods due to their computational complexity, security vulnerability, and scalability. The classical machine learning algorithms are unable to efficiently deal with the large scale and high-dimensional data that are produced by contemporary IoT systems with a high level of security assurances in an ever-changing cybersecurity threat environment. In this paper, a new quantum-inspired machine learning framework is proposed that builds on the concept of quantum computing, such as superposition, entanglement, and interference, to be able to process high-dimensional IoT information efficiently and safely. The given architecture combines quantum-inspired tensor networks with variational quantum circuits implemented in a classical manner and quantum kernel algorithms to reduce the computational complexity exponentially and offer the benefit of inherent security provided by quantum-inspired encryption and anomaly detection schemes. The new hierarchical processing pipeline reduces the high-dimensional IoT data to manageable tensors, which can be processed by the classical hardware with scaling as well as reflecting the intricate correlations across the dimensions of the data. The framework includes quantum-inspired adversarial training that can help to increase the resistance to security attacks and quantum-resistant cryptographic primitives to protect data-in-transit. The experimental analysis of multiple high-dimensional IoT datasets shows that the proposed methodology can 94.2% classify and 87% less computational effort than classical deep learning methods, and detect adversarial attacks with 99.97 accuracy level. The results prove quantum-inspired machine learning as an effective paradigm of secure, efficient, and scalable high-dimensional data processing of the IoT.
The recent convergence of 6G wireless systems and Tiny Machine Learning (TinyML) has driven the need for on-device intelligence in edge networks, where ultra-low latency, stringent energy budgets, and tight compute constraints demand novel architectures. Lightweight deep models efficiently extract local patterns but fail to capture global dependencies, while attention mechanisms do so at the expense of energy and computational cost. To bridge this gap, we introduce Quantumer, a hybrid TinyML--quantum framework that integrates multi-scale dilated convolutions and scaled dot-product attention within a lightweight transformer architecture, employing a two-stage transfer learning pipeline from Quantum Pre-Training (Quantumer-Q) to Classical Fine-Tuning (Quantumer-C). We also present QuantiblentLayer, a four-qubit variational circuit that maps compact traffic representations into measurement-based Hilbert-space features using trainable rotations and cyclic entangling operations. The circuit is used only during offline pre-training as a nonlinear embedding teacher and is removed before Quantumer-C deployment, leaving a fully classical inference model without runtime quantum execution. By transferring these quantum-assisted embeddings into an energy-efficient, lightweight transformer, Quantumer achieves strong detection performance with minimal compute and memory overhead on resource-constrained edge devices. The intrusion detection system (IDS) is used as a case study and evaluated on the Edge-IIoTset, TON IoT, and WUSTL-IIoT-2021 datasets. Quantumer-Q achieves competitive compact-model performance with 105.86K parameters, 0.4038 MB memory usage, 0.5525 MB model size, and 5.5646 MFLOPs; the INT8 Raspberry Pi 4 deployment obtains 16.8413 ms latency with a 0.6493 MB footprint. These results support training-time quantum-assisted representation learning for compact edge-deployable IDS.
The proliferation of large-scale Internet of Things (IoT) networks introduce significant challenges for real-time anomaly detection, particularly due to the massive volume, high speed, and heterogeneity of IoT-generated data. Traditional and deep learning-based models, while effective to some extent, often face computational bottlenecks that limit their scalability and responsiveness in complex IoT environments. To address these limitations, this paper investigates the application of Quantum Machine Learning (QML) for anomaly detection in IoT systems. By leveraging the parallelism and high-dimensional processing capabilities of quantum computing, QML offers a promising pathway to overcome current computational constraints. We propose a novel anomaly detection framework based on Quantum Generative Adversarial Networks (QGANs) designed to enhance security, reliability, and real-time responsiveness across diverse IoT scenarios, including smart homes, industrial IoT, healthcare monitoring, and critical infrastructure protection. Furthermore, this paper provides a comprehensive analysis of existing anomaly detection challenges, practical IoT applications, and outlines future research directions, including hybrid quantum-classical architectures, resource-efficient quantum algorithms for edge computing, and the integration of QML with emerging technologies to ensure scalable, secure, and robust IoT systems.
Escalating cyber threats and the high-dimensional complexity of IoT traffic have outpaced classical anomaly detection methods. While deep learning offers improvements, computational bottlenecks limit real-time deployment at scale. We present a quantum autoencoder (QAE) framework that compresses network traffic into discriminative latent representations and employs quantum support vector classification (QSVC) for intrusion detection. Evaluated on three datasets, our approach achieves improved accuracy on ideal simulators and on the IBM Quantum hardware demonstrating practical quantum advantage on current NISQ devices. Crucially, moderate depolarizing noise acts as implicit regularization, stabilizing training and enhancing generalization. This work establishes quantum machine learning as a viable, hardware-ready solution for real-world cybersecurity challenges.