Plenary Talk
ICEP-ITA 2024
Prof. Akmal Rustamov
Kimyo International University in Tashkent (KIUT)
Advanced Spoofing Detection for GNSS-Enabled Devices: Leveraging AI and ML Methodologies
Abstract
The low power of Global Navigation Satellite Signals (GNSS) can lead to disruptions in the performance of GNSS receivers due to anthropogenic radio frequency interferences, particularly intentional jamming and spoofing activities. While there's a prevailing belief supported by literature that modern GNSS-equipped Android smartphones are generally resilient to basic spoofing attempts, this paper aims to scrutinize this notion further. In this study, we employed advanced techniques including Artificial Intelligence (AI) and Machine Learning (ML) to enhance our analysis. Leveraging AI and ML methodologies, we refined our spoofing detection technique by harnessing the power of computational algorithms to identify patterns and anomalies in raw GNSS measurements. This approach enabled us to develop a robust and efficient method for detecting spoofing attacks on GNSS-equipped devices, such as contemporary Android smartphones, without requiring access to their low-level signal processing. Through the integration of AI and ML, our study offers a sophisticated solution to address the emerging challenges posed by spoofing activities in GNSS systems. Additionally, we propose a robust spoofing detection method that exploits the spatial and temporal correlation of counterfeit signals through statistical analysis of raw GNSS measurements. This solution doesn't necessitate access to the low-level signal processing of the GNSS receiver and can be applied to any device equipped with a GNSS receiver providing raw measurements, such as contemporary Android smartphones. Vulnerability assessment and validation of the proposed technique were conducted in a controlled environment by transmitting authentic counterfeit Global Positioning System L1/CA navigation signals to various Android smartphones with different GNSS chipsets. Our study demonstrates that, given appropriate conditions, these devices are susceptible to such attacks, with discernible effects observable in their raw measurements, including Carrier-to-noise ratio (C/N0), pseudo-range measurements, and position estimates. Particularly, we highlight that the cross-correlation between the C/N0 time series from different GNSS satellites increases under spoofing conditions, serving as an effective metric for detecting the attack within a few seconds.
Biography
Akmal Rustamov is a member of IEEE, MDPI and a distinguished academic and researcher in the field of mechanical engineering. Born in Samarkand, Uzbekistan, he has made significant contributions to his field through both his academic work and professional engagements.
Rustamov received his B.Sc. and M.Sc. degrees in mechanical engineering from Politecnico di Torino in Italy. He further pursued his Ph.D. at the same institution, specializing in electronics and telecommunications. His doctoral research focused on the study and implementation of anti-spoofing countermeasures for smartphones and unmanned aerial vehicles, highlighting his interest in GNSS (Global Navigation Satellite System) security (Polito) (KIUT). Since 2021, Rustamov has been serving as the head of the Department of Mechanical Engineering at Kimyo International University in Tashkent (KIUT). His department is involved in various cutting-edge research areas, including renewable energy, electrical engineering, and mechatronics. He has overseen several scientific grants and projects, such as TEMPUS, ERASMUS, and EDISU (KIUT).
Throughout his career, Rustamov has published extensively, with over 25 scientific papers, including articles in international journals. His work includes contributions to conferences and journals on GNSS spoofing, anti-spoofing defenses, and cooperative positioning for consumer devices (Polito). Rustamov's academic contributions and leadership in mechanical engineering are well-recognized, and he remains an active member of several professional societies, including the Italian Society of Mechanical Engineers and the Society of Automotive Engineers (KIUT).
ICEP-ITA 2024
Prof. Keekeun Lee
Electrical and Computer Engineering Department at Ajou University
Implementing Surface Acoustic Wave (SAW) Sensors for Diagnosing Power Facilities
Abstract
Partial discharge (PD) originates from faults in the insulation covering power lines, caused by impurities, voids, defects, aging, and deterioration. Continuous electrical stress rapidly worsens these faults, leading to insulation shorts, breakdowns, power outages, arcs, corona, and large-scale fires. PD emits energy in the form of charge flow, ultrasonic waves, electromagnetic waves, and light, which can be detected using appropriate sensors. Early diagnosis of PD and preemptive measures can prevent large-scale disasters. Types of PD include internal PD, surface PD, corona, and arcing, each varying in wavelength, frequency, and intensity. Surface acoustic wave (SAW) sensors, which do not apply current or voltage directly to the sensing material, are less susceptible to Joule heating and sensing material defects. They offer stable sensor characteristics, excellent sensitivity, and are easy to use in all-in-one portable wireless sensor systems. This presentation introduces wireless sensors and interface electronics for diagnosing power facilities based on surface acoustic waves, including sensors for detecting corona, a gas sensor directly inserted inside a transformer, and PD sensors. Our SAW sensor shows an ultra-fast response/recovery time of just 0.5/1 second, setting a new record in SAW-based UV sensor technology. The sensor's performance was systematically assessed in a controlled and stable environment, effectively compensating for external influences such as temperature and humidity. The optimized sensor demonstrated an impressive sensitivity of 15,787 ppm (mW/cm²)⁻¹ with a minimum detection limit of 11.5 nW/cm² for corona discharge, along with excellent repeatability and long-term stability. This presentation also introduces an analytical working mechanism to elucidate the sensing mechanism of the sensor. Rigorous experimental characterizations confirmed the robustness of both the sensor and the interface electronics, establishing them as reliable tools for real-time monitoring of PDs (corona, arc, UV-C, etc.). The presented sensor holds significant promise for widespread application across diverse fields.
Biography
He is currently a Professor in the Electrical and Computer Engineering Department at Ajou University, South Korea. He received his master’s degree from the University of Florida, USA, in 1993, and his Ph.D. degree in Electrical and Computer Engineering from Arizona State University, USA, in 2000. Following his Ph.D., he worked as a Postdoc. and an Assistant Research Professor in the Bioengineering Department at Arizona State University for three years. For the past 10 years, he has conducted intensive research on surface acoustic wave (SAW)-based sensors, including corona, PD, arcs, pressure sensors, magnetic sensors, and gas sensors. Over this period, he has published over 100 SCI papers and registered over 10 US patents. Approximately 90% of his published SCI papers are in top-tier journals, such as Advanced Materials, ACS Sensors, Nanoscale, Sensors and Actuators B, and ACS Applied Materials & Interfaces. The SAW sensors he has developed demonstrate world record-level sensitivity and response time, and are expected to have a significant impact across various application fields, establishing a strong foothold in the large sensor market with new technology. He has led various large-scale national projects and served as the project leader for the KIAT Semiconductor Major Track (2022~), CK Specialization Project (2015~), and NEXT National Project (2009~). He won the Best Teaching Award at Ajou University in 2016. Currently, he is serving as a Vice President at KIEE (C-Division; Electrical and Physical Properties, and Its Applications) and is an organizing committee chair for this ICEP-ITA conference.