Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models
Published by
Applied Soft Computing
Summary
journal-article
Kacper Sowka
About
Kacper Sowka is a PhD student at Coventry University in partnership with HORIBA MIRA with a background in Computer Science. He completed his Computer Science Bsc at Coventry University in 2020 with first class honours and has since stayed on to complete a PhD in cybersecurity and artificial intelligence as applied to automotive cybersecurity. Kacper's research is focused on the automatic generation of attack trees for automotive cybersecurity supported by machine learning. He is studying the ways in which machine learning methods could be applied in order to produce attack trees which can discern emergent and unexpected behaviour in ways that traditional formal methods of attack tree generation struggle with. This is supported by the use of vulnerability datasets and procedures such as natural language processing combined with graph neural networks to implement a comprehensive generation methodology for attack trees.
Education
Coventry University
United Kingdom of Great Britain and Northern Ireland
→
Publications
A Review on Automatic Generation of Attack Trees and Its Application to Automotive Cybersecurity
Published by
Artificial Intelligence and Cyber Security in Industry 4.0
Summary
book-chapter
Application of an Automotive Assurance Case Approach to Autonomous Marine Vessel Security
Summary
conference-paper
Application of an Automotive Assurance Case Approach to Autonomous Marine Vessel Security
Published by
2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)
Summary
conference-paper
Requirements for the automated generation of attack trees to support automotive cybersecurity assurance
Published by
WCX SAE World Congress Experience, Detroit, United States, 5/04/22
Summary
conference-paper