Post-quantum ready multimodal federated learning for adaptive threat defence

Abstract

Federated learning (FL) is a key enabler for collaborative intelligence across distributed, privacy-sensitive critical infrastructures, but multimodal FL is constrained by data heterogeneity, modality misalignment, and insecure information fusion, limiting real-time threat detection under emerging post-quantum threats. We propose PQ-FedCMCA, integrating soft cross-modal contrastive learning at the client level (adaptive scaling/relaxation for flexible many-to-many alignment) with a cross-attention-based global–local aggregation mechanism at the server level, plus knowledge distillation for generalisation. Experiments on benchmark datasets show PQ-FedCMCA outperforms state-of-the-art FL methods in cross-modal retrieval and classification tasks while enhancing post-quantum-aware privacy preservation and robustness. The framework advances trustworthy, privacy-preserving, post-quantum-aware AI for secure, adaptive threat detection in next-generation critical infrastructures.