학술논문

Artificial Intelligence (AI) and Machine Learning (ML)-based Information Security in Electric Vehicles: A Review
Document Type
Conference
Source
2023 5th Global Power, Energy and Communication Conference (GPECOM) Power, Energy and Communication Conference (GPECOM), 2023 5th Global. :108-113 Jun, 2023
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Engineering Profession
Fields, Waves and Electromagnetics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Deep learning
Electric potential
Machine learning algorithms
Government
Information security
Intrusion detection
Authentication
Machine learning
Cyber warfare
Electric vehicles
Cyber Security
Electric Vehicles
Machine Learning
Artificial intelligence
Prevention
Language
ISSN
2832-7675
Abstract
The use of artificial intelligence (AI) and machine learning (ML) in electric vehicles (EVs) is gaining popularity as a means of improving information security. However, there is a lack of research on the specific ways in which Artificial intelligence (AI) and machine learning (ML) are being used in this context. This review aims to provide an overview of the current state of Artificial intelligence (AI) and machine learning (ML)-based information security in EVs. We conducted a systematic literature search to identify relevant studies and articles and analyzed them to identify common themes and trends. Our findings show that Artificial intelligence (AI) and machine learning (ML) are being used in a variety of ways to improve information security in EVs, including in the areas of authentication, intrusion detection, and attack prevention. In particular, we found that the use of ML algorithms such as deep learning and neural networks is becoming increasingly prevalent in these applications. Additionally, we found that there is a growing interest in the use of blockchain technology in combination with Artificial intelligence (AI) and machine learning (ML) for EV information security. Our research gathered that about 75% of the studies in the field are focused on intrusion detection, 20% on authentication, and 5% on attack prevention. The majority of the studies (70%) are based on the use of deep learning, 15% of them use neural networks, and the rest of the studies use other algorithms.