Context: Advanced cyber-attacks can massively disrupt the physical systems such electric vehicle (EV) infrastructure. It is not always possible to protect the system against potential threats and the available detection capabilities may not be enough. Therefore, it is vital to understand that the system is under attack, its potential impact and react with appropriate cyber incident responses. Intelligent edge devices embedded with AI/machine learning can help preparing the systems against cyber-attack responses with situational awareness. This work will consider possible EV charging bit configurations including sent to and from the controller, and the patterns between these input/output bit configurations. Then apply both, supervised and unsupervised machine learning algorithms to detect malicious data instances and attack patterns, and prepare businesses with effective and adaptive responses (analytic monitoring, separation, and dynamic representation) against cyber-attacks.
The School of Computer Science & Informatics has a strong emphasis on cyber security research due to recent grants, and also hosts the Airbus Centre of Excellence for Cyber Security and NCSC approved Academic Centres of Excellence in Cyber Security Research (ACE-CSR). Students attend research workshops and conferences, skills training through the Doctoral Academy, and have an opportunity to work with industry. A healthy research environment promotes research ideas and collaborations, and opportunities for networking through interdisciplinary work with the School of Engineering (Energy/EV research group). The students will be part of the Sustainable Transport Interdisciplinary Doctoral Training Hub (https://idth-sustainable-transport.org/) benefiting from training and activities, and can also interact with DTE Network+ (https://dte.network/).
Objectives: The objectives of this work are: (1) Identify potential cyber threats and risks; (2) Integrate situational awareness and forensics elements to incident-response techniques to develop a simulation tool/technique; (3) Developing a response model using AI/ML for mitigating identified risks.
- Surveys on risk, impact and state of the art: cyber incident-response of electric vehicle infrastructure
- Identifying advanced cyber incidents and indicators of compromise
- Assess cyber risks and evaluate effective incident-response techniques
- Develop response model applying AI/ML techniques to mitigate identified risks.
- Academic technical publications
Dr Neetesh Saxena
Prof Liana Cipcigan
Prof Omer Rana
This is a self funded project.
A 2:1 or above Honours undergraduate degree or a master’s degree, in computing or a related subject. Applicants for whom English is not their first language must demonstrate their proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.
Please contact Dr. Neetesh Saxena to discuss this project.
For an overview of the programme, tuition fees and other information, visit the website here.
Read the How to Apply tab, and in the Apply box choose qualification Doctor of Philosophy in Computer Science & Informatics, mode of study Full-time. In the research proposal section of your application, specify the project title and supervisors of this project, and in the funding section, select the ‘self-funding’ option.