Due to the widespread presence of manufacturing units, real-time data collection becomes a challenging task, especially as the scale of operations continues to expand. Moreover, manufacturing industries often deal with sensitive and proprietary data and are reluctant to share data directly in areas like lithography hotspot detection (LHD) due to concerns about IP protection and regulatory compliance. Moreover, human error can lead to incorrect labeling of parts or products. Detecting hotspots in lithography is crucial for ensuring the product quality and reliability of the manufacturing process. In today's context, Federated Learning (FL) stands out as a crucial remedy, facilitating the rapid advancement of distributed machine learning while effectively managing critical concerns regarding data privacy and governance. Moreover, FL systems must be robust against not only malicious label flipping attacks but also inadvertent human errors. In recent years, the convergence of quantum computing and machine learning represents a groundbreaking interdisciplinary approach with immense potential for revolutionizing various industries ranging from healthcare to manufacturing. In this work, we proposed a Quantum Federated Learning (QFL) framework for lithography hotspot detection and offer a unique solution to address the challenges mentioned above effectively. To demonstrate the generalization ability and robustness, we performed extensive experiments with label-flipping attacks in the proposed framework. Based on our results, the global quantum model maintained a high classification accuracy and best performance even when faced with label-flipping attacks from a specific number of clients in federated learning settings, while keeping data private across manufacturing units. Moreover, a defense strategy based on clustering is proposed to distinguish the good and bad model updates from the participants in a quantum federated framework.
Due to the widespread presence of manufacturing units, real-time data collection becomes a challenging task, especially as the scale of operations continues to expand. Moreover, manufacturing industries often deal with sensitive and proprietary data and are reluctant to share data directly in areas like lithography hotspot detection (LHD) due to concerns about IP protection and regulatory compliance. Moreover, human error can lead to incorrect labeling of parts or products. Detecting hotspots in lithography is crucial for ensuring the product quality and reliability of the manufacturing process. In today's context, Federated Learning (FL) stands out as a crucial remedy, facilitating the rapid advancement of distributed machine learning while effectively managing critical concerns regarding data privacy and governance. Moreover, FL systems must be robust against not only malicious label flipping attacks but also inadvertent human errors. In recent years, the convergence of quantum computing and machine learning represents a groundbreaking interdisciplinary approach with immense potential for revolutionizing various industries ranging from healthcare to manufacturing. In this work, we proposed a Quantum Federated Learning (QFL) framework for lithography hotspot detection and offer a unique solution to address the challenges mentioned above effectively. To demonstrate the generalization ability and robustness, we performed extensive experiments with label-flipping attacks in the proposed framework. Based on our results, the global quantum model maintained a high classification accuracy and best performance even when faced with label-flipping attacks from a specific number of clients in federated learning settings, while keeping data private across manufacturing units. Moreover, a defense strategy based on clustering is proposed to distinguish the good and bad model updates from the participants in a quantum federated framework.
The geographical dispersion of manufacturing units introduces challenges related to latency, network connectivity, data synchronization, communication overhead, scalability, data security, and resource allocation. Manufacturing data often includes sensitive information related to proprietary processes, designs, and technologies. Companies are hesitant to share this data such as lithography hotspot data (LHD) directly due to concerns about privacy and the risk of intellectual property theft. Federated learning provides a solution to address these challenges by allowing companies to collaboratively train models without sharing raw data. It allows companies to adhere to privacy laws while benefiting from shared insights. In recent years, the convergence of quantum machine learning has demonstrated transformative potential by leveraging quantum principles to address complex problems across various industries. In this work, a concept of quantum federated learning consisting of variational quantum circuit is proposed to address the lithography hotspot sharing challenges by providing a privacy-preserving, centralized, and quantum-enhanced framework. It combines the collaborative advantages of federated learning with the unique capabilities of quantum computing, offering a solution that is secure, scalable, and adaptable to the complexities of modern manufacturing environments. The performance evaluations involve scalability and robustness, particularly in the context of label-flipping attacks, which is crucial for validating, optimizing, and enhancing the quantum federated learning framework's applicability to real-world challenges in the manufacturing sector.
Healthcare organizations have a high volume of sensitive data and traditional technologies have limited storage capacity and computational resources. The prospect of sharing healthcare data for machine learning is more arduous due to government regulations related to patient privacy. In recent years, federated learning has offered a solution to accelerate distributed machine learning addressing concerns related to data privacy and governance. Currently, the blend of quantum computing and machine learning has experienced significant attention from academic institutions and research communities. The ultimate objective of this work is to develop a federated quantum machine learning framework (FQML) to tackle the optimization, security, and privacy challenges in the healthcare industry for medical imaging tasks. In this work, we propose a new methodology based on federated quantum convolutional neural networks (QCNNs) with distributed training across edge devices. To demonstrate the feasibility of the proposed FQML framework, we performed extensive experiments on two benchmark medical datasets (Pneumonia MNIST, and CT kidney disease analysis), which are non-independently and non-identically partitioned among the healthcare institutions/clients. The proposed framework is validated and assessed via large-scale simulations. Based on our results, the quantum simulation experiments achieve performance levels on par with well-known classical CNN models, 86.3% accuracy on the pneumonia dataset and 92.8% on the CT-kidney dataset, while requiring fewer model parameters and consuming less data. Moreover, a client selection mechanism is proposed to reduce the computation overhead at each communication round, which effectively improves the convergence rate.
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.
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.
Anomaly detection has a significant impact on applications such as video surveillance, medical diagnostics, and industrial monitoring, where anomalies frequently depend on context and anomaly-labeled data are limited. Quantum federated learning (QFL) overcomes these concerns by distributing model training among several quantum clients, consequently eliminating the requirement for centralized quantum storage and processing. However, in real-life quantum networks, clients frequently differ in terms of hardware capabilities, circuit designs, noise levels, and how classical data is encoded or preprocessed into quantum states. These differences create inherent heterogeneity across clients - not just in their data distributions, but also in their quantum processing behaviors. As a result, training a single global model becomes ineffective, especially when clients handle imbalanced or non-identically distributed (non-IID) data. To address this, we propose a new framework called personalized quantum federated learning (PQFL) for anomaly detection. PQFL enhances local model training at quantum clients using parameterized quantum circuits and classical optimizers, while introducing a quantum-centric personalization strategy that adapts each client's model to its own hardware characteristics and data representation. Extensive experiments show that PQFL significantly improves anomaly detection accuracy under diverse and realistic conditions. Compared to state-of-the-art methods, PQFL reduces false errors by up to 23%, and achieves gains of 24.2% in AUROC and 20.5% in AUPR, highlighting its effectiveness and scalability in practical quantum federated settings.
Abstract Currently, data privacy and security are critical in deep learning, especially with biometric data. Federated learning (FL) addresses these concerns, but struggles with security, complexity, and high-dimensional data. Quantum Federated Learning (QFL) overcomes these issues by combining FL with quantum computing, thereby offering greater power and parallelism. In this paper, we propose an innovative QFL approach with a quantum–classical hybrid architecture to address the limitations of classical FL and achieve superior performance in video and image classification. The proposed architecture consists of a classical server and quantum–classical clients. On the client side, after preprocessing the videos and images, a pre-trained model extracts high-level features, which are then classified by a client-specific quantum circuit using a Variational Quantum Circuit (VQC). To maximize the performance of this hybrid system, we jointly optimize the VQC parameters and the weights of the pre-trained model’s final feature-extraction layers. The proposed approach has been extensively evaluated in a simulation environment with random client selection to account for the heterogeneity of real-world systems. Furthermore, we present results obtained from quantum computers using globally optimized VQC parameters. This successful validation on actual quantum hardware underscores the practical applicability of our approach, extending its significance beyond theoretical contributions to next-generation applications such as smart campus security.