#federated learning Preprint

Differential Privacy in Feature Reconstruction Aided Federated Learning for Agent's Semantic Communication Model Update

Yoon Huh Bumjun Kim Wan Choi

Aug 2026 · 2 citations · 12 references

Engineering

TL;DR

Experimental results on multiple datasets show that the proposed DP-aided FedSFR outperforms DP-enabled FedAvg in training stability and image reconstruction quality in heterogeneous wireless systems.

Abstract

This paper proposes a differentially private federated learning (FL) framework built upon an FL algorithm with semantic feature reconstruction (FedSFR) for training semantic communication modules for image transmission. By allowing clients with unfavorable uplink capacity to transmit low-dimensional semantic feature vectors extracted from locally trained joint source-channel coding (JSCC) encoders, FedSFR enhances communication efficiency and training stability under heterogeneous wireless conditions. To protect client privacy, we incorporate the oneshot Laplace mechanism and theoretically demonstrate that feature-based transmission achieves strictly stronger differential privacy (DP) guarantees than gradient-based transmission under an identical communication budget. In addition, a model selection mechanism is introduced to alleviate performance degradation caused by privacy-preserving perturbations. Experimental results on multiple datasets show that the proposed DP-aided FedSFR outperforms DP-enabled FedAvg in training stability and image reconstruction quality in heterogeneous wireless systems.

arXiv Semantic Scholar

View source

Similar papers

Conference Aug 2026

An Adaptive Differential Privacy Framework for Secure Cloud Edge Federated Learning using Gradient Norm Dynamics

The concept of Federated Learning (FL) allows training models in a decentralized way without distributing raw data but, nonetheless, the gradients are vulnerable to privacy attacks that include gradient inversion, reconstruction, and membership inference. Differential Privacy (DP) is broadly used to address these risks...

Vajjakeshavulu Anusha, Ranjeeth Kumar M · 2026 International Conferenc... · 0 citations

2026

Differential Privacy Enabled Cascaded Filter for Efficient and Privacy-Preserving Federated Learning

Federated learning (FL) enables collaborative model training across multiple clients in a privacy-preserving manner. However, the employment of homomorphic encryption algorithms might lead to high computational cost while the application of differential privacy (DP) methods would sacrifice model performance. To establi...

Zhiqiang Chen, Yuchen Jiang, Ray Y. Zhong et al. · IEEE Transactions on Informa... · 0 citations

Preprint Aug 2026

Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

Experimental results on heterogeneous MNIST and CIFAR-10 settings show that QEF-GT-AdamW consistently improves robustness and convergence performance over representative DecL baselines while achieving favorable accuracy-communication trade-offs under limited wireless resources.

Thieu Van Nguyen, T. Nguyen, Ons Aouedi et al. · 0 citations

Open access Sep 2025

Adaptive Dual-Mode Distillation for Robust and Communication-Efficient Federated Learning Under Statistical and Model Heterogeneity

The growing volume of data from smart devices offers significant potential for machine learning, yet privacy concerns hinder centralized use. Federated Learning (FL) has emerged as a promising decentralized learning (DL) approach enabling the use of distributed data without compromising privacy. However, practical depl...

Zahid Iqbal, Fatima N. al-Aswadi, Haziqah Shamsudin et al. · IEEE Access · 0 citations

Conference Aug 2026

Federated Learning Architectures and Communication-Efficient Optimisation for Privacy-Preserving Distributed AI Systems

Federated learning (FL) trains a shared model across data holders that cannot pool their records, but deployments remain bounded by three coupled costs: uplink traffic from repeated model exchange, accuracy loss under statistically heterogeneous clients, and the information that updates still leak. These are usually at...

Harshavardhan Peddireddy, Sandeep Kumar Gadde, Prasad Bheemavarapu et al. · 2026 International Conferenc... · 0 citations

#federated learning Conference Aug 2026

Federated learning-based privacy-preserving multisource data fusion for smart grids

This study addresses the challenges of privacy leakage and data silos in multi-source heterogeneous data interaction within smart grids by designing a federated multi-source data fusion architecture that combines adaptive local differential privacy with feature space alignment. This architecture utilizes Hessian matrix...

Jia-Ying Li, Can Pei · International Conference on... · 0 citations

Differential Privacy in Feature Reconstruction Aided Federated Learning for Agent's Semantic Communication Model Update

Abstract

Similar papers

An Adaptive Differential Privacy Framework for Secure Cloud Edge Federated Learning using Gradient Norm Dynamics

Differential Privacy Enabled Cascaded Filter for Efficient and Privacy-Preserving Federated Learning

Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

Adaptive Dual-Mode Distillation for Robust and Communication-Efficient Federated Learning Under Statistical and Model Heterogeneity

Federated Learning Architectures and Communication-Efficient Optimisation for Privacy-Preserving Distributed AI Systems

Federated learning-based privacy-preserving multisource data fusion for smart grids

Related blog posts

Discovering the value of humanistic inquiry

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

MIT announces the MIT for America initiative, to strengthen STEM education across the country

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance