The field of cybersecurity is moving towards the integration of quantum machine learning and federated learning to enhance privacy, efficiency, and robustness. Researchers are exploring the potential of quantum machine learning to improve network intrusion detection and quantum key distribution. Federated learning is being investigated as a means to preserve data privacy in distributed machine learning applications, particularly in heterogeneous networks such as the Internet of Vehicles. Noteworthy papers include:

• A survey on adapting federated and quantum machine learning for network intrusion detection, which provides a comprehensive analysis of federated learning architectures and quantum machine learning approaches.
• A paper on evaluating relayed and switched quantum key distribution network architectures, which compares the performance of two architectures and identifies optimal key management configurations.
• A study on mapping quantum threats to cryptographic dependencies, which presents a systematic inventory of technologies exposed to quantum threats and guides practitioners in identifying vulnerable systems.
• A proposal for FedCLF, a federated learning approach with calibrated loss and feedback control, which enhances model accuracy and optimizes resource utilization in heterogeneous networks.