DP-EMAR: A Differentially Private Framework for Autonomous Model Weight Repair in Federated IoT Systems

TL;DR

DP-EMAR is a novel framework that detects and corrects transmission errors in federated IoT systems, ensuring privacy and improving convergence stability despite communication challenges.

Contribution

It introduces a differentially private error repair framework that autonomously detects and reconstructs transmission distortions during federated learning in IoT networks.

Findings

Preserves convergence stability under communication corruption.

Maintains near baseline performance with strict differential privacy guarantees.

Enhances robustness and trust in federated IoT learning.

Abstract

Federated Learning (FL) enables decentralized model training without sharing raw data, but model weight distortion remains a major challenge in resource constrained IoT networks. In multi tier Federated IoT (Fed-IoT) systems, unstable connectivity and adversarial interference can silently alter transmitted parameters, degrading convergence. We propose DP-EMAR, a differentially private, error model based autonomous repair framework that detects and reconstructs transmission induced distortions during FL aggregation. DP-EMAR estimates corruption patterns and applies adaptive correction before privacy noise is added, enabling reliable in network repair without violating confidentiality. By integrating Differential Privacy (DP) with Secure Aggregation (SA), the framework distinguishes DP noise from genuine transmission errors. Experiments on heterogeneous IoT sensor and graph datasets show that DP-EMAR preserves convergence stability and maintains near baseline performance under communication corruption while ensuring strict (epsilon, delta)-DP guarantees. The framework enhances robustness, communication efficiency, and trust in privacy preserving Federated IoT learning.