NORMA eResearch @NCI Library

Detection of Replay Attacks in Autonomous Vehicles LTV Systems using Dynamic Watermarking, Kalman Filter and Mahalanobis Distance

Syed Jaffar, Taher Ahmed (2024) Detection of Replay Attacks in Autonomous Vehicles LTV Systems using Dynamic Watermarking, Kalman Filter and Mahalanobis Distance. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (1MB) | Preview

Abstract

A strong replay attack in autonomous vehicle would lead to traffic disruptions, compromise of sensitive data and could also put the passenger’s life at risk. Considering the evolution of autonomous vehicle and its corresponding complications of replay attack, this paper focuses on proposing a solution to detect replay attacks in autonomous vehicle’s CAN bus model. Although there are various research strategies proposed on this category, the prime idea behind this research paper aims to study about the Linear Time Varying (LTV) systems which handles the core dynamics of the self driving vehicles and accountable for handling deviations in the varied conditions. This is achieved by combining dynamic watermarking with Kalman Filter and Mahalanobis Distance to estimate the state of dynamic system and handle correlated variables of CAN bus data effectively. The technique is investigated by creating a simulation bed acting as a CAN bus model to transmit messages between each nodes, and the data is extracted from Apollo Scape which consists a largescale trajectory data of urban streets with traffic flows containing vehicles, riders and pedestrians. Here, the replay attack was triggered and tested at different intervals and has resulted with higher recall rate for LTV systems with 77%, an average of 0.10 seconds detection rate, and predicting the freshness of each messages efficiently.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Mustafa, Raza Ul
UNSPECIFIED
Uncontrolled Keywords: Linear Time Varying (LTV); Kalman Filter; Mahalanobis Distance; Dynamic Watermarking
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 28 Jul 2025 14:00
Last Modified: 28 Jul 2025 14:00
URI: https://norma.ncirl.ie/id/eprint/8266

Actions (login required)

View Item View Item