A MACHINE LEARNING-BASED INTRUSION DETECTION SYSTEM FOR IOT ELECTRIC VEHICLE CHARGING STATIONS (EVCS)/ Mohamed Ahmed Hassan ElKashlan

Supervisor:
Heba Aslan

Thesis (M.A.)—Nile University, Egypt, 2023 .

"Includes bibliographical references"

Contents:
Contents
CERTIFICATION OF APPROVAL.................................................................................iii
DEDICATION.................................................................................................................. vii
ACKNOWLEDGEMENTS............................................................................................... ix
TABLE OF CONTENTS................................................................................................... xi
LIST OF FIGURES ......................................................................................................... xiii
LIST OF TABLES............................................................................................................ xv
ACRONYMS.................................................................................................................. xvii
PUBLICATIONS............................................................................................................. xix
ABSTRACT..................................................................................................................... xxi
CHAPTER 1 INTRODUCTION ........................................................................................ 1
1.1 Introduction....................................................................................................1
1.2 Problem definition .........................................................................................2
1.3 Motivation......................................................................................................4
1.4 Intrusion detection in IoT...............................................................................5
1.5 Thesis Contributions......................................................................................7
CHAPTER 2 BACKGROUND .......................................................................................... 8
2.1 EVCS background .........................................................................................8
2.2.1 Attacks on the EVCS ................................................................................10
2.2.2 Users’ Attacks...........................................................................................11
xii
2.2.3 Power Grid Attacks...................................................................................12
2.3 EVCS and IoT..............................................................................................14
CHAPTER 3 RELATED WORK..................................................................................... 19
3.1 Related Research..........................................................................................19
3.2 Literature review..........................................................................................20
CHAPTER 4 METHODOLOGY ..................................................................................... 31
4.1. Introduction.................................................................................................31
4.2. Dataset description......................................................................................33
4.3. IoT-23 Dataset ............................................................................................33
4.4. Selected features .........................................................................................35
4.5. Machine Learning Classifiers.....................................................................41
4.6. Experimental setup......................................................................................48
CHAPTER 5 SIMULATION ........................................................................................... 51
5.1 Evaluation Metrics.......................................................................................51
5.1.1 Confusion matrix ......................................................................................51
5.1.2 Precision....................................................................................................52
5.1.3 Accuracy ...................................................................................................52
5.1.4 Recall Score ..............................................................................................52
5.1.5 F-1 Score...................................................................................................52
5.2. Experimental Results..................................................................................53
5.2.1 Binary Classification results.....................................................................55
5.2.2 Multiclass classification results ................................................................57
CHAPTER 6 CONCLUSION AND FUTURE WORK ................................................... 62
6.1 Discussion and Limitations..........................................................................62
6.2 Conclusion and Future Work.......................................................................64
REFERENCES ................................................................................................................. 65

Abstract:
The market for Electric Vehicles (EVs) has expanded tremendously as seen in the
recent Conference of the Parties 27 (COP27) held at Sharm El Sheikh, Egypt in
November 2022. This needs the creation of an ecosystem that is user-friendly and
secure. Internet connected Electric Vehicle Charging Stations (EVCSs) provide
rich user experience and add-on services. Eventually, the EVCSs are connected to
a management system, which is the Electric Vehicle Charging Station
Management System (EVCSMS). Attacking the EVCS ecosystem is rising at the
same rate as those of physical attacks and vandalism happening on the physical
EVCSs. The cyberattack is more severe than the physical attack as it may affect
thousands of EVCSs at the same time. Intrusion Detection is vital in defending
against diverse types of attacks and unauthorized activities. Fundamentally, the
Intrusion Detection System’s (IDS) problem is a classification problem. The IDS
tries to find out if each traffic stream is legitimate or malicious. Furthermore, the
IDS can identify the type of malicious traffic. In this study, we address IoT
security issues in EVCS, by using different machine learning techniques that were
created to address other, non-IoT security challenges. We also compare different
machine learning classifier algorithms for detecting different kinds of attacks in
the EVCS network environment. A typical Internet of Things (IoT) dataset
obtained from actual IoT traffic is used in the study. We compare classification
algorithms that are used in the Intrusion detection systems that are placed inline to
xxii
the traffic. This traffic contains different types of attacks targeting the EVCS
network. The results obtained from this research improve the stability of the
EVCS system and significantly reduce the amount of cyberattacks that could
disrupt the daily life activities associated with the EVCS ecosystem

Text in English, abstracts in English.