Novel position falsification attacks detection in the Internet of Vehicles using machine learning

• Main Authors: Ilango, Harun Surej, Ma, Maode, Su, Rong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering; Engineering::Electrical and electronic engineering; Engineering::Electrical and electronic engineering::Wireless communication systems; Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Internet of Vehicles; Position Falsification Attacks; Machine Learning; Novel Attack Detection; Basic Safety Messages (BSMs); VeReMi Dataset; Vehicle-to-Vehicle (V2V) Communication; Anomaly Detection
• Online Access: https://hdl.handle.net/10356/167113
• Institution: Nanyang Technological University

In an Internet of Vehicles (IoV) network, vehicles periodically broadcast Basic Safety Messages (BSMs) that contain the vehicle's current position, speed, and acceleration. Safety-critical applications like blind-spot warning and lane change warning systems use these BSMs to ensure the safety of road users. However, an attacker can affect the efficacy of such applications by injecting false information into the messages. One such attack is the position falsification attack, where the attacker inserts incorrect information regarding the vehicle's position in the BSMs. The literature has explored the use of Misbehavior Detection Systems (MDSs) to detect position falsification attacks. But the limitation of the existing MDSs is that they are signature-based and require prior knowledge about the attacks for effective detection. To overcome this shortcoming, we propose a Novel Position Falsification Attack Detection System for the Internet of Vehicles (NPFADS for the IoV)that learns and detects new position falsification attacks emerging in IoV networks. The performance of NPFADS is quantitatively measured using the metrics precision, recall, F1 score, and ROC. The Vehicular Reference Misbehavior (VeReMi) dataset is used as the benchmark to analyze the performance of NPFADS. The performance of NPFADS is compared to existing MDSs in the literature, and the analysis shows that NPFADS performs on par with the existing signature-based detection models even when initialized with zero initial knowledge.