The number of IoT devices continues to rise and it is imperative to detect anomalies in real-time to ensure the security, reliability and efficiency of the system. Current deep neural network models have great memory and computing requirements, so it is not easy to use on the edge device. The benefit of federated learning is that it leaves raw data on the individual device, thus improving privacy. Nonetheless, efficient feature learning by compressing the size of quantum datasets has not been built into current federated learning frameworks, and the efficacy of quantum-based approaches under realistic noise in the hardware have not been widely investigated. To address privacy concerns, QEdgeNet is a lightweight hybrid quantum-classical federated learning (QLFL) model for anomaly detection in edge-IoT networks . In this model, the features of network traffic are first compressed by principal component analysis, and then the network traffic is mapped to a compact 4-qubit variational quantum circuit for the classification of anomalous traffic. This model is an aggregated model updated using the Cheon-Kim-Kim-Song (CKKS) homomorphic encryption mechanism, but without exposing the raw network data of clients, and raw traffic data never escapes from a client device during the training process. The applicability of the suggested approach in an idealized simulator is quantified by measuring the inference performance in a simulator simulated quantum hardware noise, the accuracy loss from the hardware noise is recovered by extrapolating to zero noise.
The number of IoT devices continues to rise and it is imperative to detect anomalies in real-time to ensure the security, reliability and efficiency of the system. Current deep neural network models have great memory and computing requirements, so it is not easy to use on the edge device. The benefit of federated learning is that it leaves raw data on the individual device, thus improving privacy. Nonetheless, efficient feature learning by compressing the size of quantum datasets has not been built into current federated learning frameworks, and the efficacy of quantum-based approaches under realistic noise in the hardware have not been widely investigated. To address privacy concerns, QEdgeNet is a lightweight hybrid quantum-classical federated learning (QLFL) model for anomaly detection in edge-IoT networks . In this model, the features of network traffic are first compressed by principal component analysis, and then the network traffic is mapped to a compact 4-qubit variational quantum circuit for the classification of anomalous traffic. This model is an aggregated model updated using the Cheon-Kim-Kim-Song (CKKS) homomorphic encryption mechanism, but without exposing the raw network data of clients, and raw traffic data never escapes from a client device during the training process. The applicability of the suggested approach in an idealized simulator is quantified by measuring the inference performance in a simulator simulated quantum hardware noise, the accuracy loss from the hardware noise is recovered by extrapolating to zero noise.
We propose a Quantum Federated Autoencoder for Anomaly Detection, a framework that leverages quantum federated learning for efficient, secure, and distributed processing in IoT networks. By harnessing quantum autoencoders for high-dimensional feature representation and federated learning for decentralized model training, the approach transforms localized learning on edge devices without requiring transmission of raw data, thereby preserving privacy and minimizing communication overhead. The model leverages quantum advantage in pattern recognition to enhance detection sensitivity, particularly in complex and dynamic IoT network traffic. Experiments on a real-world IoT dataset show that the proposed method delivers anomaly detection accuracy and robustness comparable to centralized approaches, while ensuring data privacy.
We propose FedTQK, a federated quantum kernel learning framework for anomaly detection in resource-constrained Internet of Things (IoT) networks. FedTQK is an ultra-lightweight hybrid detector: a local classical autoencoder compresses raw traffic, only twenty-four parameters of a shared parameterized quantum circuit (PQC) are exchanged with the server each round, and anomalies are decided by a one-class support vector machine defined on the resulting quantum kernel. The distinguishing property of FedTQK is not detection accuracy but the per-round communication footprint. Each per-round upload occupies 96 uplink bytes per client, which fits inside a single Low-Power Wide-Area Network (LPWAN) uplink frame at moderate spreading factors; measured across a full twenty-round, ten-client training schedule, the aggregate uplink drops from 1,536.7 KiB (a classical federated averaging autoencoder baseline evaluated on the same schedule) to 18.75 KiB. This reduction is a structural property of quantum kernel embeddings, whose parameter count grows with the number of trainable rotations rather than with the size of a classical weight tensor, and it is therefore expected to extrapolate to substantially higher-dimensional detection problems in which transmitting a classical model each round would exceed the IoT device duty cycle. FedTQK is intended for the regime in which the communication budget is the binding constraint and accuracy parity with strong classical baselines—not accuracy dominance—is the acceptable ceiling. Experiments on NSL-KDD confirm that FedTQK attains an accuracy that numerically overlaps with a classical federated averaging autoencoder baseline and with a purely local, non-federated reference. The results quantify the communication reduction relative to the classical baseline and identify the local non-federated variant as the natural reference against which the value of federation should be judged.
In this paper, we propose a Federated Variational Quantum Machine Learning (F-VQML) framework tailored for anomaly detection in smart IoT infrastructures. First, we introduce a localized quantum feature embedding strategy that mitigates the dimensionality bottleneck, allowing resource-constrained edge nodes to efficiently encode time-series data into Hilbert space. Second, we integrate a federated learning architecture where nodes collaboratively train Variational Quantum Circuits (VQCs) by exchanging only parameterized quantum gradients, thereby ensuring strict data privacy and bypassing the need for raw data transmission. Finally, we evaluate the robustness of the F-VQML framework against realistic hardware noise models, specifically depolarizing and Pauli noise channels. Comprehensive simulations on network intrusion datasets reveal that our approach achieves a 94.2% anomaly detection accuracy. Furthermore, it reduces communication overhead by 98% compared to classical deep federated architectures, all while maintaining resilience to NISQ-era depolarizing noise.
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.
The rapid growth of industrial Internet of Things (IIoT) systems has created new challenges for anomaly detection in high-dimensional, multivariate time-series, where privacy, scalability, and communication efficiency are critical. Classical federated learning approaches mitigate privacy concerns by enabling decentralized training, but they often struggle with highly non-linear decision boundaries and imbalanced anomaly distributions. To address this gap, we propose a Federated Quantum Kernel Learning (FQKL) framework that integrates quantum feature maps with federated aggregation to enable distributed, privacy-preserving anomaly detection across heterogeneous IoT networks. In our design, quantum edge nodes locally compute compressed kernel statistics using parameterized quantum circuits and share only these summaries with a central server, which constructs a global Gram matrix and trains a decision function (e.g., Fed-QSVM). Experimental results on synthetic IIoT benchmarks demonstrate that FQKL achieves superior generalization in capturing complex temporal correlations compared to classical federated baselines, while significantly reducing communication overhead. This work highlights the promise of quantum kernels in federated settings, advancing the path toward scalable, robust, and quantum-enhanced intelligence for next-generation IoT infrastructures.
The edge computing environment faces a challenge in maintaining data privacy while performing machine learning tasks. The current solutions for privacy preservation are inefficient or do not provide security guarantees, causing a critical gap in the edge computing environment, which is resource-constrained. The aim of this research work is to design a hybrid quantum-classical computing system that addresses the challenges of privacy preservation and efficiency in machine learning tasks. We design a novel architecture combining variational quantum circuits for secure data encoding with classical neural networks for scalable inference, implemented through federated learning protocols enhanced with quantum differential privacy mechanisms. Experimental evaluation demonstrates a 35% reduction in communication overhead compared to traditional federated learning approaches while maintaining 99.2% classification accuracy across diverse datasets. The quantum-enhanced privacy mechanisms achieve provable security guarantees with information-theoretic bounds, outperforming conventional cryptographic methods by 28% in computational overhead reduction. This hybrid approach establishes a new paradigm for secure and efficient machine learning deployment on edge devices, enabling privacy-preserving artificial intelligence in healthcare, finance, and IoT applications.