Advances in Secure and Accurate Localization Systems

The field of localization systems is moving towards more secure and accurate methods, with a focus on detecting and mitigating malicious attacks. Researchers are exploring the use of machine learning and deep learning techniques to improve the security and reliability of localization systems. One of the key challenges is the vulnerability of these systems to spoofing attacks, which can have severe consequences. To address this, researchers are proposing novel approaches such as self-supervised federated learning frameworks and extended receiver autonomous integrity monitoring frameworks. These approaches aim to improve the resilience of localization systems against location spoofing attacks and provide more accurate location data. Noteworthy papers include: Self-Supervised Federated GNSS Spoofing Detection with Opportunistic Data, which proposes a self-supervised federated learning framework for GNSS spoofing detection that outperforms position-based and deep learning-based methods. Securing WiFi Fingerprint-based Indoor Localization Systems from Malicious Access Points, which proposes a long-term reliable indoor localization scheme that detects malicious APs and mitigates their effects, achieving a detection accuracy above 95% for each attack type.

Sources

Self-Supervised Federated GNSS Spoofing Detection with Opportunistic Data

A Comprehensive Data Description for LoRaWAN Path Loss Measurements in an Indoor Office Setting: Effects of Environmental Factors

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

ML-Enabled Eavesdropper Detection in Beyond 5G IIoT Networks

Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories

Hybrid Wi-Fi/PDR Indoor Localization with Fingerprint Matching

A Practical Approach to Generating First-Order Rician Channel Statistics in a RC plus CATR Chamber at mmWave

Guardian Positioning System (GPS) for Location Based Services

Built with on top of