Aug 2026· Frontiers of Physics· Vol 14· 0 citations· 36 references
TL;DR
Experiments 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.
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.
This research proposes a privacy-preserving, federated learning-based deep-fake detection framework that facilitates secure, decentralized training across heterogeneous devices and affirm that combining multimodal feature learning with federated intelligence offers a powerful and ethically aligned solution to emerging...
Federated learning is appealing for privacy-sensitive network systems, yet its practical deployment remains hindered by the following three recurring challenges: (1) client drift under non-IID data, (2) vulnerability to corrupted updates, and (3) the communication cost of repeated model exchange. Most existing approach...
Hua Kun, Wei Wang· 2026 International Conferenc...· 0 citations
SplittingFed-DP relocates the Gaussian DP mechanism from the high-dimensional gradient to the low-dimensional activation space at the cut layer, audited under Rényi differential privacy and proves that this same Gaussian release coincides with the randomised-smoothing operator of Cohen et al. at the cut layer.
Rguibi Arjdal, Y. Asimi, Ahmed Asimi et al.· EPJ Web of Conferences· 0 citations
This work proposes a lightweight and information-theoretically secure aggregation framework that securely computes the majority vote (MV) polynomial through single-round secure multiplication, ensuring end-to-end information-theoretic security under the honest-majority assumption while revealing only the final aggregat...
These findings demonstrate that the proposed framework provides an effective balance between privacy preservation, adversarial robustness, and trustworthy decentralized collaborative learning for secure AI-driven systems.
Durga Sivan, Uma Maheshwari Shanmugam, Sachnev Vasily et al.· Discover Artificial Intellig...· 0 citations
Deep learning is becoming popular in cloud applications and serves to provide intelligent services; data aggregation in a central location makes sensitive information vulnerable to privacy breaches, regulatory infractions, and adversarial manipulation. All modern privacy mechanisms offer partial protection and frequent...
Sribidhya Mohanty, Pallavi Gupta, Anil Pratap Singh et al.· 2026 International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
