Publication

Image of a publication paper

Modern cyber domain is an extremely complex field to master. There are numerous capricious dependencies between networked systems and data. In cyber security, technology has a major role, but the knowledge and skills of the individuals combined with the incident response processes of the organisations are even more important assets. Those assets foster the cyber Cyber Range Technical Federation: Case Flagship 1 Exercise

Image of a publication paper

The implementation of cybersecurity research, development, and training and education at different levels strengthens both national expertise and Finland as an information society. Several strategies have been published at the EU and national levels with the aim of improving cybersecurity expertise and facilitating research, education, and innovation in the field. The current research project promoted Cybersecurity education in universities of applied sciences

Image of a publication paper

This paper presents an analysis of Bachelor’s and Master’s cybersecurity theses in Jyväskylä, Finland. The theses were gathered from publicly available publishing platforms of Finnish universities and were analysed using the NICE Cybersecurity Workforce Framework (NCWF) categories and European Cyber Security Organization’s (ECSO) The European Cybersecurity Taxonomy. The aim of this research was to find Analysing Finnish Cybersecurity Thesis Topics Using Taxonomic Frameworks

Image of a publication paper

One-pixel attack is a curious way of deceiving neural network classifier by changing only one pixel in the input image. The full potential and boundaries of this attack method are not yet fully understood. In this research, the successful and unsuccessful attacks are studied in more detail to illustrate the working mechanisms of a one-pixel Chromatic and Spatial Analysis of One-Pixel Attacks Against an Image Classifier

Image of a publication paper

Automatic medical image diagnosis tools are vulnerable to modern model fooling technologies. Because medical imaging is a way of determining the health status of a person, the threats could have grave consequences. These threats are not only dangerous to the individual but also threaten the patients’ trust in modern diagnosis methods and in the healthcare Model Fooling Threats Against Medical Imaging

Image of a publication paper

Most research and development on Cyber Security education is currently focusing on what should be taught, how much, and where within the degree programmes. Different Cyber Security frameworks are currently evolving to include Cyber Security education parallel to older paradigms of Computing Education, existing alongside with such as “Information Technology” and “Software Engineering”. Different Cyber Researching graduated cyber security students: Reflecting employment and job responsibilities through NICE framework

Image of a publication paper

The modern trend of moving artificial intelligence computation near to the origin of data sources has increased the demand for new hardware and software suitable for such environments. We carried out a scoping study to find the current resources used when developing Edge AI applications. Due to the nature of the topic, the research combined Artificial Intelligence in the IoT Era: A Review of Edge AI Hardware and Software

Image of a publication paper

In the field of medical imaging, artificial intelligence solutions are used for diagnosis, prediction and treatment processes. Such solutions are vulnerable to cyberattacks, especially adversarial attacks targeted at machine learning algorithms. One-pixel attack is an adversarial method against image classification algorithms based on neural networks. In this study, we show that a variational autoencoder can Detecting One-Pixel Attacks Using Variational Autoencoders