SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization

TL;DR

SAFELOC is a federated learning framework that enhances indoor localization accuracy and robustness against data poisoning attacks while maintaining a compact model suitable for mobile devices.

Contribution

It introduces a fused neural network architecture and a dynamic saliency map-based aggregation strategy for robust, efficient, and privacy-preserving indoor localization in heterogeneous device environments.

Findings

Up to 5.9x reduction in mean localization error.

Up to 7.8x reduction in worst-case localization error.

2.1x decrease in model inference latency.

Abstract

Machine learning (ML) based indoor localization solutions are critical for many emerging applications, yet their efficacy is often compromised by hardware/software variations across mobile devices (i.e., device heterogeneity) and the threat of ML data poisoning attacks. Conventional methods aimed at countering these challenges show limited resilience to the uncertainties created by these phenomena. In response, in this paper, we introduce SAFELOC, a novel framework that not only minimizes localization errors under these challenging conditions but also ensures model compactness for efficient mobile device deployment. Our framework targets a distributed and co-operative learning environment that uses federated learning (FL) to preserve user data privacy and assumes heterogeneous mobile devices carried by users (just like in most real-world scenarios). Within this heterogeneous FL context, SAFELOC introduces a novel fused neural network architecture that performs data poisoning detection and localization, with a low model footprint. Additionally, a dynamic saliency map-based aggregation strategy is designed to adapt based on the severity of the detected data poisoning scenario. Experimental evaluations demonstrate that SAFELOC achieves improvements of up to 5.9x in mean localization error, 7.8x in worst-case localization error, and a 2.1x reduction in model inference latency compared to state-of-the-art indoor localization frameworks, across diverse building floorplans, mobile devices, and ML data poisoning attack scenarios.