Federated Learning (FL) is emerging as a distributed privacy-preserving paradigm, aiming to build a strong machine learning (ML) model in a distributed manner. Client selection in FL is a critical challenge for building intrusion detection systems, especially in heterogeneous Internet of Things (IoT) networks, where Non-Independent and Identically Distributed (Non-IID) data partitioning causes classical selection strategies to suffer from catastrophic forgetting of minority attack classes. This paper presents a Quantum Approximate Optimization Algorithm (QAOA) based framework that formulates client selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem encoding client utility, communication latency, a cardinality constraint, and an optional group diversity term, solved at each communication round using the QAOA. To reduce quantum circuit width for near-term hardware compatibility, we investigate two qubit reduction strategies in this paper: hierarchical client clustering and classical pre-filtering. Extensive experiments on three IoT intrusion detection benchmarks under heterogeneous Non-IID distributions show that our proposed approach improves macro F1-score by up to 30% over Greedy-TopK selection and by up to 29% over random client selection. Our ablation studies confirm that the quantum-assisted selection advantage emerges specifically under Non-IID distributions. On the most challenging dataset, where two attack categories represent less than 0.5% of the data, the proposed method achieves superior results than other client selection methods on aggregate metrics while offering superior precision and convergence stability.
Federated Learning (FL) is emerging as a distributed privacy-preserving paradigm, aiming to build a strong machine learning (ML) model in a distributed manner. Client selection in FL is a critical challenge for building intrusion detection systems, especially in heterogeneous Internet of Things (IoT) networks, where Non-Independent and Identically Distributed (Non-IID) data partitioning causes classical selection strategies to suffer from catastrophic forgetting of minority attack classes. This paper presents a Quantum Approximate Optimization Algorithm (QAOA) based framework that formulates client selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem encoding client utility, communication latency, a cardinality constraint, and an optional group diversity term, solved at each communication round using the QAOA. To reduce quantum circuit width for near-term hardware compatibility, we investigate two qubit reduction strategies in this paper: hierarchical client clustering and classical pre-filtering. Extensive experiments on three IoT intrusion detection benchmarks under heterogeneous Non-IID distributions show that our proposed approach improves macro F1-score by up to 30% over Greedy-TopK selection and by up to 29% over random client selection. Our ablation studies confirm that the quantum-assisted selection advantage emerges specifically under Non-IID distributions. On the most challenging dataset, where two attack categories represent less than 0.5% of the data, the proposed method achieves superior results than other client selection methods on aggregate metrics while offering superior precision and convergence stability.
Quantum Federated Learning (QFL) has recently emerged as a promising paradigm for privacy-preserving distributed intelligence in Internet of Things (IoT) environments. In this paper, we introduce QFedDefend, a quantum federated defense framework that integrates local variational quantum learners, quantum-secure aggregation, quantum differential privacy, and a quantum kernel-based adversarial detection layer to protect IoT systems against poisoning attacks, adversarial client updates, and inference attacks. Unlike prior studies that mainly explore theoretical advantages of quantum machine learning or isolated components of secure aggregation, QFedDefend provides a unified architecture designed specifically for adversarial and resource-constrained IoT environments. The framework combines hybrid quantum-classical learning at the edge with secure global aggregation and trust-aware update validation. The proposed approach is evaluated on the Edge-IIoTset dataset and further validated on UNSW-NB15 to assess cross-dataset generalization. Experimental results demonstrate strong performance across predictive accuracy, robustness, and privacy-aware operation. In the external validation scenario, QFedDefend achieves 99% accuracy, 99% precision, 99% recall, and 99% F1-score, confirming its ability to generalize effectively across heterogeneous IoT security datasets. These findings demonstrate that QFL can serve as a strong and practical solution for security-critical IoT environments when implemented through an integrated architecture such as QFedDefend. The paper contributes both a deployable framework and a comprehensive empirical study positioning quantum federated learning as an effective next-generation defense strategy for industrial and large-scale IoT systems.
Federated learning (FL) is a widely used method for training machine learning (ML) models in a scalable way while preserving privacy (i.e., without centralizing raw data). Prior research shows that the risk of exposing sensitive data increases cumulatively as the number of iterations where a client's updates are included in the aggregated model increase. Attackers can launch membership inference attacks (MIA; deciding whether a sample or client participated), property inference attacks (PIA; inferring attributes of a client's data), and model inversion attacks (MI; reconstructing inputs), thereby inferring client-specific attributes and, in some cases, reconstructing inputs. In this paper, we mitigate risk by substantially reducing per client exposure using a quantum computing-inspired quadratic unconstrained binary optimization (QUBO) formulation that selects a small subset of client updates most relevant for each training round. In this work, we focus on two threat vectors: (i) information leakage by clients during training and (ii) adversaries who can query or obtain the global model. We assume a trusted central server and do not model server compromise. This method also assumes that the server has access to a validation/test set with global data distribution. Experiments on the MNIST dataset with 300 clients in 20 rounds showed a 95.2% per-round and 49% cumulative privacy exposure reduction, with 147 clients' updates never being used during training while maintaining in general the full-aggregation accuracy or even better. The method proved to be efficient at lower scale and more complex model as well. A CINIC-10 dataset-based experiment with 30 clients resulted in 82% per-round privacy improvement and 33% cumulative privacy.
Federated Learning (FL) trains a global model across decentralized clients while preserving data privacy, but at scale it is vulnerable to malicious updates. Byzantine-resilient aggregation methods such as MultiKrum score gradients against their nearest neighbors and can miss malicious updates that preserve the statistical properties of honest ones. We propose a quantum annealing approach that reformulates client selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem, encoding pairwise distances into a cost function solved by quantum annealers (QA). Unlike MultiKrum's greedy per-client scoring, the QUBO formulation jointly optimizes over all subsets to find the mutually closest group of m clients. At small scale (15 clients), QUBO outperforms MultiKrum on the most challenging Byzantine attacks: e.g., Advanced LIE is detected with 95.11% accuracy versus 81.33% on MNIST and 97.78% versus 75.56% on CIFAR-10. QUBO fares poorly on simpler attacks where MultiKrum excels, so the two methods are complementary. QUBO quality also degrades as the number of clients grows. To address this, we introduce a MultiSignal ensemble that uses a dual-feature routing gate based on Euclidean and cosine Krum score gaps to classify attacks into four regimes and routes evasion attacks to a suspicion-penalized QUBO with agreement voting. At 100 clients on MNIST, MultiSignal achieves 95.3% average detection accuracy versus 91.8% for classical MultiKrum, with the largest gains on Sparse Lie (72.0% to 95.2%, +23.2 points) and Advanced Lie (80.4% to 85.2%, +4.8 points). These results show that QUBO-based quantum annealing with MultiSignal is a principled and scalable defense against the most challenging Byzantine strategies in federated learning.
In recent years, the growing demand for secure, efficient, and scalable machine learning has highlighted significant challenges in traditional Federated Learning (FL) systems. These challenges include computational inefficiencies in handling large-scale, high-dimensional data, privacy concerns, and the limitations of classical hardware in solving complex optimization problems. Additionally, the increasing complexity of data and the need for more robust privacy-preserving methods have pushed the boundaries of classical FL. To address these issues, this paper presents a detailed framework for Quantum Federated Learning (QFL), where quantum computing and FL converge to enable distributed quantum model training with enhanced privacy preservation. The system is modeled using local quantum models on clients and a global aggregation strategy at the server. We develop quantum gradient-based optimization with quantum cross-entropy loss, privacy preservation through encryption, and robustness to quantum noise. A set of theorems is provided to prove the correctness and efficiency of the model, supported by rigorous mathematical formulations. We used IBM Qiskit for the simulation and compared our proposed QFL with classical FL. The results demonstrate that our QFL outperformed classical FL in terms of accuracy, precision, recall, and F1 score.
Abstract This paper addresses Quantum Federated Learning (QFL), an adaptation of classical federated learning for quantum computing that enables collaboration among multiple quantum devices. A significant challenge in QFL arises from non-independent and identically distributed (non-IID) data, primarily due to inherent variations in quantum devices and environments, which substantially degrades performance. To mitigate this, we propose novel QFL algorithms that employ weighted averaging and clustering-optimized averaging strategies. Specifically, Quantum Weighted Federated Averaging (QW-FedAvg) is introduced, which utilizes a model aggregation strategy combining quantum weighted averaging with a global data-sharing mechanism to reduce the impact of non-IID data. Building on this, we further propose the Quantum Federated Clustering-Optimized Averaging (QF-COA) algorithm. QF-COA enhances performance by selecting client-side training parameters that demonstrate superior efficacy through a clustering method, thereby further minimizing the adverse effects of non-IID data on model performance. Our models were trained and evaluated using the MNIST and Fashion-MNIST datasets. Simulation results demonstrate that the proposed algorithms improve accuracy by 2% to 5% in non-IID environments compared to traditional quantum federated averaging algorithms. Additionally, these advancements lead to enhanced communication efficiency and increased robustness. These improvements contribute to the greater generalization and adaptability of QFL frameworks, offering both theoretical insights and practical guidance for future research in the field. The source code is available at https://github.com/wang-lab-repository/qavg-gzq.git .
Federated learning (FL) is a privacy-preserving alternative to centralized machine learning, where model training is performed on local devices and only global model updates are shared, effectively addressing challenges, such as data silos and privacy protection. Recently, quantum FL (QFL), an emerging FL branch, has garnered significant attention in many industry applications. However, existing QFL algorithms predominantly employ average weighting for global model training, which shows poor performance on heterogeneous healthcare data. To address this challenge, this study proposes a dynamic aggregation QFL algorithm (DAQFL) for intelligent diagnosis. Specifically, it utilizes quantum neural networks (QNNs) as local training models and designs corresponding variational quantum circuits (VQC). To mitigate performance degradation caused by the heterogeneity of medical industrial data, a dynamic aggregation method based on accuracy is proposed to enhance global model performance effectively. Extensive experiments with three distribution settings, including independent and identically distributed (IID), non-independent and identically distributed (Non-IID), and long-tail datasets, show that DAQFL outperforms baseline algorithms in accuracy and training speed. It also performs well in privacy protection and robustness of anti-noise, improving its suitability for real-world medical applications.