GPS-IDS: An Anomaly-based GPS Spoofing Attack Detection Framework for Autonomous Vehicles (2405.08359v2)

Abstract: Autonomous Vehicles (AVs) heavily rely on sensors and communication networks like Global Positioning System (GPS) to navigate autonomously. Prior research has indicated that networks like GPS are vulnerable to cyber-attacks such as spoofing and jamming, thus posing serious risks like navigation errors and system failures. These threats are expected to intensify with the widespread deployment of AVs, making it crucial to detect and mitigate such attacks. This paper proposes GPS Intrusion Detection System, or GPS-IDS, an Anomaly-based intrusion detection framework to detect GPS spoofing attacks on AVs. The framework uses a novel physics-based vehicle behavior model where a GPS navigation model is integrated into the conventional dynamic bicycle model for accurate AV behavior representation. Temporal features derived from this behavior model are analyzed using machine learning to detect normal and abnormal navigation behaviors. The performance of the GPS-IDS framework is evaluated on the AV-GPS-Dataset -- a GPS security dataset for AVs comprising real-world data collected using an AV testbed, and simulated data representing urban traffic environments. To the best of our knowledge, this dataset is the first of its kind and has been publicly released for the global research community to address such security challenges.

• The paper introduces GPS-IDS, a framework that uses anomaly behavior analysis and a physics-based model to identify GPS spoofing attacks on autonomous vehicles.
• It integrates a fusion of a GPS navigation model with a dynamic bicycle model to accurately capture expected vehicle behavior patterns.
• The system's evaluation on the newly released AV-GPS-Dataset confirms its effectiveness in enhancing autonomous vehicle security.

The paper "GPS-IDS: An Anomaly-based GPS Spoofing Attack Detection Framework for Autonomous Vehicles" addresses a significant security challenge faced by autonomous vehicles (AVs): GPS spoofing attacks. These attacks can induce navigation errors and potential system failures, posing serious threats to the safe operation of AVs, especially as their deployment becomes more widespread.

The authors propose GPS-IDS, an intrusion detection system that uses Anomaly Behavior Analysis (ABA) to identify GPS spoofing attempts. At the heart of this system is a novel physics-based vehicle behavior model, which integrates a GPS navigation model with a conventional dynamic bicycle model. This fusion allows for a more accurate representation of expected AV behavior. By analyzing temporal features derived from this behavior model, the system employs machine learning techniques to differentiate between normal and abnormal navigation behaviors.

The framework's effectiveness is tested using the AV-GPS-Dataset, a real-world dataset collected through an AV testbed set up by the research team. This dataset, considered the first of its kind, has been publicly released to aid further research in addressing security challenges associated with AV GPS systems.

The significance of this work lies in its robust approach to detecting GPS spoofing and its contribution to the research community through the release of the AV-GPS-Dataset. By offering a reliable method for identifying malicious GPS interference, the paper represents an important step in fortifying AV navigation systems against cyber threats.