Securing WiFi Fingerprint-based Indoor Localization Systems from Malicious Access Points

TL;DR

The paper tackles the security challenge of RSSI perturbations from malicious APs in WiFi fingerprint-based indoor localization. It presents a lightweight, long-term scheme with online malicious-AP detection based on variance and mean-difference tests and mitigation via imputation using $p$ LGBMRegressor$s, complemented by SRCC-based correlated AP selection, normalization, and noise augmentation in the offline database. Key contributions include a practical detection accuracy above $95\%$ for all attack types and a mitigation strategy that restores performance close to the no-malicious-AP baseline, along with a substantial reduction in execution time (about $94\%$ faster) compared to prior work. The approach enhances robustness and reduces maintenance costs by avoiding frequent database reconstructions while supporting dynamic environments and long-term operation.

Abstract

WiFi fingerprint-based indoor localization schemes deliver highly accurate location data by matching the received signal strength indicator (RSSI) with an offline database using machine learning (ML) or deep learning (DL) models. However, over time, RSSI values degrade due to the malicious behavior of access points (APs), causing low positional accuracy due to RSSI value mismatch with the offline database. Existing literature lacks the detection of malicious APs in the online phase and mitigating their effects. This research addresses these limitations and proposes a long-term, reliable indoor localization scheme by incorporating malicious AP detection and their effect mitigation techniques. The proposed scheme uses a Light Gradient-Boosting Machine (LGBM) classifier to estimate locations and integrates simple yet efficient techniques to detect malicious APs based on online query data. Subsequently, a mitigation technique is incorporated that updates the offline database and online queries by imputing stable values for malicious APs using LGBM Regressors. Additionally, we introduce a noise addition mechanism in the offline database to capture the dynamic environmental effects. Extensive experimental evaluation shows that the proposed scheme attains a detection accuracy above 95% for each attack type. The mitigation strategy effectively restores the system's performance nearly to its original state when no malicious AP is present. The noise addition module reduces localization errors by nearly 16%. Furthermore, the proposed solution is lightweight, reducing the execution time by approximately 94% compared to the existing methods.

Figures (6)

• Figure 1: System model.
• Figure 2: Overview of the proposed scheme.
• Figure 3: Impact of noise addition.
• Figure 4: Performance analysis of the proposed scheme.
• Figure 5: Performance comparison between AAIFU and proposed schemes.