Abstract: | Global Navigation Satellite Systems (GNSS) are a core component in critical infrastructure and the primary source of maritime navigation. In recent years, a widespread occurrence of GNSS spoofing incidents have been noted, impacting not only military but increasingly commercial maritime operations. Several developments in resilient PNT for vessels focus on receiver and antenna design, including use of dual-band and multi-constellation receivers, anti-jamming/spoofing algorithms along with signal authentication protocols such as OSNMA for Galileo. While these works are a crucial step towards GNSS cybersecurity, they do not offer complete protection because attackers constantly find new vulnerabilities and improve their methods; in contrast, existing defenses detect very specific patterns of attack and thus may be evaded in a variety of ways. Our work aims at developing an enhanced situational awareness tool for GNSS which serves as an additional layer of security to address vulnerabilities within the existing infrastructure and support ongoing developments in resilient PNT for vessels. By monitoring and modeling patterns in site-specific GNSS signals at the RF, syntactic, and semantic levels, we can give defenders a kind of situational awareness for GNSS. Just as situational awareness allows attacks to be detected and countered on a battlefield, GNSS situational awareness allows attacks in that theater to be detected as deviations from previously observed patterns. Further, because we are using combinations of simpler models rather than complex, aggregated machine learning methods such as deep learning, our methods are suitable for embedded applications, including as a layer of on-receiver defense. Our methods are also very amenable to explainable AI, allowing us to both detect anomalies and explain why they are anomalous. GNSS situational awareness can function as both a stopgap for vulnerabilities affecting vessels without the latest defenses as well as enhanced security for those equipped with more robust systems, thus addressing the needs of today and securing against future threats. |
Published in: |
Proceedings of the 37th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2024) September 16 - 20, 2024 Hilton Baltimore Inner Harbor Baltimore, Maryland |
Pages: | 560 - 573 |
Cite this article: | Bhundar, Harsimrat, Somayaji, Anil, Dutt, Deepak, Dutt, Swetha, "GNSS Attack Detection Through Situational Awareness," Proceedings of the 37th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2024), Baltimore, Maryland, September 2024, pp. 560-573. https://doi.org/10.33012/2024.19902 |
Full Paper: |
ION Members/Non-Members: 1 Download Credit
Sign In |