Federated learning (FL) is a distributed machine learning paradigm with a promising future, which can preserve data privacy while training the global model collaboratively. However, FL is still facing model confidentiality issues. Therefore, in this paper, we propose a quantum key distribution (QKD) based secure FL scheme to facilitate FL model encryption against network eavesdropping attacks. Specifically, we introduce a stochastic resource allocation scheme for QKD to support FL networks. In the network, remote FL workers are connected to the server to train an aggregated global model in a distributed manner. However, due to the unpredictable number of workers at each location, the demand for secret-key rates to support secure model transmission to the server is not uniform. The proposed scheme can allocate QKD resources (i.e., wavelengths) in a way that minimizes the total cost given the stochastic demand. We formulate the optimization problem for the proposed scheme as a stochastic programming model. Numerical results demonstrate that the proposed scheme can successfully achieve the cost-minimizing objective while satisfying all uncertain demands and other security constraints.
Federated learning (FL) is a distributed machine learning paradigm with a promising future, which can preserve data privacy while training the global model collaboratively. However, FL is still facing model confidentiality issues. Therefore, in this paper, we propose a quantum key distribution (QKD) based secure FL scheme to facilitate FL model encryption against network eavesdropping attacks. Specifically, we introduce a stochastic resource allocation scheme for QKD to support FL networks. In the network, remote FL workers are connected to the server to train an aggregated global model in a distributed manner. However, due to the unpredictable number of workers at each location, the demand for secret-key rates to support secure model transmission to the server is not uniform. The proposed scheme can allocate QKD resources (i.e., wavelengths) in a way that minimizes the total cost given the stochastic demand. We formulate the optimization problem for the proposed scheme as a stochastic programming model. Numerical results demonstrate that the proposed scheme can successfully achieve the cost-minimizing objective while satisfying all uncertain demands and other security constraints.
Increasing privacy and security concerns in intelligence-native 6G networks require quantum key distribution-secured federated learning (QKD-FL), in which data owners connected via quantum channels can train an FL global model collaboratively without exposing their local datasets. To facilitate QKD-FL, the architectural design and routing management framework are essential. However, effective implementation is still lacking. To this end, we propose a hierarchical architecture for QKD-FL systems in which QKD resources (i.e., wavelengths) and routing are jointly optimized for FL applications. In particular, we focus on adaptive QKD resource allocation and routing for FL workers to minimize the deployment cost of QKD nodes under various uncertainties, including security requirements. The experimental results show that the proposed architecture and the resource allocation and routing model can reduce the deployment cost by 7.72% compared to the CO-QBN algorithm.
Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without direct data sharing, addressing privacy concerns. However, traditional FL is vulnerable to attacks targeting model updates, potentially compromising data privacy. This paper proposes a novel decentralized federated learning framework that integrates quantum key distribution (QKD) to establish secure keys for data aggregation. The core claim is that QKD significantly enhances the security and efficiency of FL. The proposed system utilizes QKD to generate and distribute shared keys between participating devices, enabling secure aggregation of model updates while mitigating the risk of individual data exposure. This approach directly addresses the security vulnerabilities inherent in standard FL. The framework's architecture relies on a decentralized network topology, further bolstering resilience against single points of failure. Mathematical formulations detailing key aspects of the system, including key distribution protocols, aggregation processes, and security analysis, are presented. This work represents a significant advancement in secure FL by combining the strengths of two cutting-edge technologies: FL and QKD.
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.
Machine learning models in online environments are vulnerable to various adversarial attacks, such as those from generative adversarial networks (GANs) attacks and more powerful attacks based on recent advances in quantum computing. Federated Learning (FL), a modern privacy preserving distributed machine learning technique, also faces modern data management concerns related to quantum computing. Limiting adversarial learning through quantum mechanics lends itself as an effective security mechanism. This paper introduces a novel quantumencrypted FL framework that integrates randomly-generated quantum noise into an FL environment to improve security against adversarial learning algorithms. These algorithms can conduct reconstruction attacks, which increase privacy leakage through adversarially generated data. Specifically, GAN attacks are effective at creating data samples that resemble training data. Traditional computing techniques can be improved by appending random noise generated by quantum computers as a quantum verification method. The proposed hybrid-quantum encryption approach can fortify a network against generative reconstruction attacks by adding quantum noise to each participant's training data samples. To evaluate the effectiveness of the proposed quantum encryption techniques for protecting FL against GANs, we encrypt the MNIST dataset with quantum-generated keys and then distribute the data in a privacy-preserving manner.
With rapid developments of artificial intelligence (AI) and wireless communication technologies, autonomous vehicular networks (AVNs) have emerged to provide convenient, comfortable, and safe driving services. Especially, due to the provable and unconditional security, quantum communication technology is increasingly being applied to promote the security of data delivery in AVNs, which forms the promising quantum AVNs (QAVNs). Federated learning (FL) is essential in QAVNs to implement intelligent and autonomous driving, where extensive distributed data is utilized to cooperatively train AI models, preserve user privacy, and reduce resource consumption. However, the FL unavoidably faces several possible privacy and security problems as a result of the intricate interconnections between several autonomous vehicles or infrastructures. In this article, we investigate the security and privacy of FL in QAVNs. Specifically, we first establish the system architecture, including quantum key distribution protocol, space-air-ground integrated network (SAGIN)-enabled QAVNs model, and FL framework in QAVNs. Furthermore, we describe the privacy and security threats to FL in QAVNs, i.e., inference attack, eavesdropping attack, and sybil attack. Following that, we give a case study for designing a secure FL scheme using the local differential privacy mechanism and the homomorphic encryption mechanism. Finally, we suggest several potential future research directions in QAVNs.
Federated Learning (FL) allows the model to be trained cooperatively and retain the locality of data, but the exchange of model updates between dispersed clients and a central server can be compromised and manipulated. In this paper, a secure communication system of federated learning integrating quantum key distribution with the use of the BB84 protocol to enhance the establishment of secure keys is introduced. The suggested structure will achieve the use of QKD-generated symmetric keys along with classical cryptography tools to secure the privacy and integrity of model update messages. Federated learning communication and key generation, authentication, and encryption overheads are modeled at a system-level by developing a simulation environment. Parameters introduced to the simulation include the model update size, the number of clients, the communication latency and the cost of key refresh, which allows a more detailed examination of the system performance and feasibility. The findings show that the introduction of QKD is associated with limited and deterministic overhead on the communication latency and key management, and no convergence of the learning process is lost. This paper will concentrate on communication-layer security and will not consider the learning-layer threats e.g., adversarial model poisoning or client malicious behavior. These results show that quantum-secured key exchange can be integrated into federated learning systems and emphasize that it is a key enabling technology of secure communication in distributed learning systems in the future.