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.
The rapid evolution of AI-generated synthetic media, called deepfakes, has raised substantial concerns regarding digital misinformation, security breaches, and public trust. Existing centralized detection systems are often limited with privacy risks, weak generalizability, and reduced robustness when exposed to multimodal manipulations across audio, text, and video data. There is always a human cognitive capacity to fuse and contrast cues across sensory modalities while judging authenticity. This research proposes a privacy-preserving, federated learning-based deep-fake detection framework that facilitates secure, decentralized training across heterogeneous devices. The proposed framework leverages Fed-DFakeNet for localized model training, enabling robust feature extraction from multimodal datasets without transmitting raw data. It incorporates MogDetNet, a knowledge distillation-based fusion module that aligns multimodal features for improved generalization and accuracy. Furthermore, the mCreamFL aggregation strategy introduces a contrastive representation ensemble and encrypted communication mechanism, ensuring data integrity and optimal performance while preserving user privacy. Comprehensive experiments are conducted using three benchmark datasets FoR (audio), SDFVD (video), and TweepFake (text) demonstrating superior performance. The framework achieves classification accuracies of 98.32%, 99.43%, and 99.87%, significantly outperforming state-of-the-art baselines. Evaluation metrics such as sensitivity, F-measure, and G-mean reinforce the framework’s reliability, robustness, and resilience against adversarial content. This study contributes a scalable and secure deepfake detection pipeline and underscores the critical importance of privacy-aware AI systems in combating the increasing sophistication of generative media. The results affirm that combining multimodal feature learning with federated intelligence offers a powerful and ethically aligned solution to emerging digital threats.
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 approaches address these issues in isolation. While analytically convenient, this separation often fails to reflect real-world conditions. For instance, defenses against poisoning may suppress useful updates, while personalization and compression can alter the aggregation geometry itself. In this paper, we study these effects jointly and propose URP-FL, a compact training framework that integrates reliability-aware aggregation, local regularization for drift control, and sparse client uploads. We provide theoretical analysis establishing a convergence bound with distinct terms capturing optimization error, data heterogeneity, and adversarial impact. Experiments on a non-IID image classification benchmark with sign-flip and label-flip attacks demonstrate the benefits of the unified design. Compared to FedAvg and FedProx, this URP-FL maintains accuracy under attack while reducing transmitted parameters by approximately 75%. Rather than presenting a production ready system, it offers a reproducible and technically coherent step toward federated learning that is more robust under realistic conditions.
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 aggregated sign to the server.
Decentralized Federated Learning (DFL) enables collaborative artificial intelligence model training without centralizing sensitive data, making it suitable for privacy-critical and distributed intelligent systems such as healthcare, Industrial IoT, and smart digital infrastructure. Despite its advantages, DFL remains vulnerable to privacy leakage through shared model updates and to model poisoning and backdoor attacks that compromise system reliability, robustness, and trustworthiness. Existing defense mechanisms primarily address either privacy preservation or poisoning robustness independently and often exhibit limited effectiveness under adaptive or high-ratio adversarial settings. This work proposes a trustworthy and privacy-preserving decentralized federated learning framework that jointly addresses these challenges through two integrated components: (i) a hybrid privacy mechanism based on public dataset pretraining followed by differentially private fine-tuning, and (ii) a multi-layer model defense architecture designed to mitigate poisoning and backdoor attacks across decentralized peer-to-peer environments. The framework integrates local data sanitization, peer-side model verification, robust trimmed-mean aggregation, and runtime inference protection to provide defense-in-depth across both training-time and inference-time attack surfaces. An adversary model and operational assumptions are formally defined, and the framework is evaluated under strong adversarial conditions, including a 20% poisoning ratio. Experimental results demonstrate consistent robustness improvements over a vanilla DFL baseline. While the baseline model achieves a clean accuracy of 83.10%, the proposed framework improves clean performance to 86.12%. Under adversarial conditions, accuracy improves from 37.71% to 53.88% for Fast Gradient Sign Method (FGSM) attacks, from 21.75% to 46.40% for Projected Gradient Descent (PGD) attacks, and from 40.62% to 67.35% for Carlini–Wagner (CW) attacks. For backdoor-based poisoning attacks such as BadNets and Blended attacks, the defense pipeline restores model accuracy to above 86% while maintaining stable benign performance. 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 frequently lack accuracy, scalability, or practicality in their operations. To overcome these limitations, a federated deep learning model is formulated so that secure joint learning can occur without transferring raw data across the domains of ownership. The framework incorporates training that is decentralized, training that uses differential privacy, training that uses secure aggregation, training that uses encrypted communication, and training that uses trust-based anomaly defense to defend against leakage, poisoning, and inference attacks. It also supports heterogeneous and highly non-IID datasets using adaptive coordination and stability-relevant participation regulation and meets emerging data protection requirements. The methods of resource-conscious orchestration and the optimization of communication eliminate overhead without obstructing the effectiveness of learning. The paradigm has therefore formed a privacy-by-design intelligent cloud ecosystem which ensures confidentiality, maintains performance, enhances robustness, and ensures responsible AI implementation in privacy-related sectors of healthcare, finance, governance, and smart infrastructure.
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.
