Learning Attack Trees by Genetic Algorithms

DORFHUBER, Florian Sebastian, Julia EISENTRAUT and Jan KŘETÍNSKÝ. Learning Attack Trees by Genetic Algorithms. Online. In Theoretical Aspects of Computing – ICTAC 2023. Lima: Springer, 2023, p. 55-73. ISBN 978-3-031-47962-5. Available from: https://dx.doi.org/10.1007/978-3-031-47963-2_5.

Basic information

• Original name: Learning Attack Trees by Genetic Algorithms
• Authors: DORFHUBER, Florian Sebastian (276 Germany, belonging to the institution), Julia EISENTRAUT (276 Germany) and Jan KŘETÍNSKÝ (203 Czech Republic, belonging to the institution).
• Edition: Lima, Theoretical Aspects of Computing – ICTAC 2023, p. 55-73, 19 pp. 2023.
• Publisher: Springer

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Germany
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: electronic version available online
• Impact factor: Impact factor: 0.402 in 2005
• RIV identification code: RIV/00216224:14330/23:00133581
• Organization unit: Faculty of Informatics
• ISBN: 978-3-031-47962-5
• ISSN: 0302-9743
• Doi: http://dx.doi.org/10.1007/978-3-031-47963-2_5
• UT WoS: 001160556100005
• Keywords in English: genetic algorithms
• Tags: firank_B
• Tags: International impact, Reviewed

Abstract

Attack trees are a graphical formalism for security assessment. They are particularly valued for their explainability and high accessibility without security or formal methods expertise. They can be used, for instance, to quantify the global insecurity of a system arising from the unreliability of its parts, graphically explain security bottlenecks, or identify additional vulnerabilities through their systematic decomposition. However, in most cases, the main hindrance in the practical deployment is the need for a domain expert to construct the tree manually or using further models. This paper demonstrates how to learn attack trees from logs, i.e., sets of traces, typically stored abundantly in many application domains. To this end, we design a genetic algorithm and apply it to classes of trees with different expressive power. Our experiments on real data show that comparably simple yet highly accurate trees can be learned efficiently, even from small data sets.