Sec5GLoc: Securing 5G Indoor Localization via Adversary-Resilient Deep Learning Architecture

TL;DR

This paper presents Sec5GLoc, a deep learning-based indoor localization system for 5G networks that is resilient to adversarial attacks, achieving high accuracy and real-time performance by combining fingerprinting, geometric consistency, and attention mechanisms.

Contribution

We propose a novel adversary-resilient localization architecture that integrates deep learning with physical domain knowledge to defend against signal spoofing and manipulation in 5G indoor localization.

Findings

Achieves approximately 0.58 m mean error under benign conditions.

Maintains around 0.81 m error under attack scenarios.

Reduces localization errors by 4-5 times compared to baseline methods.

Abstract

Emerging 5G millimeter-wave and sub-6 GHz networks enable high-accuracy indoor localization, but security and privacy vulnerabilities pose serious challenges. In this paper, we identify and address threats including location spoofing and adversarial signal manipulation against 5G-based indoor localization. We formalize a threat model encompassing attackers who inject forged radio signals or perturb channel measurements to mislead the localization system. To defend against these threats, we propose an adversary-resilient localization architecture that combines deep learning fingerprinting with physical domain knowledge. Our approach integrates multi-anchor Channel Impulse Response (CIR) fingerprints with Time Difference of Arrival (TDoA) features and known anchor positions in a hybrid Convolutional Neural Network (CNN) and multi-head attention network. This design inherently checks geometric consistency and dynamically down-weights anomalous signals, making localization robust to tampering. We formulate the secure localization problem and demonstrate, through extensive experiments on a public 5G indoor dataset, that the proposed system achieves a mean error approximately 0.58 m under mixed Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) trajectories in benign conditions and gracefully degrades to around 0.81 m under attack scenarios. We also show via ablation studies that each architecture component (attention mechanism, TDoA, etc.) is critical for both accuracy and resilience, reducing errors by 4-5 times compared to baselines. In addition, our system runs in real-time, localizing the user in just 1 ms on a simple CPU. The code has been released to ensure reproducibility (https://github.com/sec5gloc/Sec5GLoc).