An Evidence Theoretic Approach for Traffic Signal Intrusion Detection
Date
2023
Authors
Chowdhury, A.
Karmakar, G.
Kamruzzaman, J.
Das, R.
Newaz, S.H.S.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Sensors, 2023; 23(10):4646-4646
Statement of Responsibility
Conference Name
Abstract
<jats:p>The increasing attacks on traffic signals worldwide indicate the importance of intrusion detection. The existing traffic signal Intrusion Detection Systems (IDSs) that rely on inputs from connected vehicles and image analysis techniques can only detect intrusions created by spoofed vehicles. However, these approaches fail to detect intrusion from attacks on in-road sensors, traffic controllers, and signals. In this paper, we proposed an IDS based on detecting anomalies associated with flow rate, phase time, and vehicle speed, which is a significant extension of our previous work using additional traffic parameters and statistical tools. We theoretically modelled our system using the Dempster–Shafer decision theory, considering the instantaneous observations of traffic parameters and their relevant historical normal traffic data. We also used Shannon’s entropy to determine the uncertainty associated with the observations. To validate our work, we developed a simulation model based on the traffic simulator called SUMO using many real scenarios and the data recorded by the Victorian Transportation Authority, Australia. The scenarios for abnormal traffic conditions were generated considering attacks such as jamming, Sybil, and false data injection attacks. The results show that the overall detection accuracy of our proposed system is 79.3% with fewer false alarms.</jats:p>
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)