Using a mathematical method, the researchers converted them into visual form and then passed them on to artificial intelligence. This can very successfully detect whether the software is "good" or dangerous software, i.e. malware. In addition to providing a visually compelling representation of computer malware, the proposed method increases the accuracy of its detection and provides new insights into its behaviour.

"We have developed a method that can monitor the dynamic behaviour of malware and translate it into a very nice visual form using fractal geometry, a branch of mathematics that deals with highly structured shapes and their representation. The images were then discussed with artificial intelligence, learning to tell bad software from good. We handed her about 130,000 images in two types of experiments, half of which were goodware and half malware. Then we presented her with completely unknown viruses and asked her to evaluate them. She was able to recognize the malware with a success rate of up to 91 percent and is still improving," described the method's author Ivan Zelinka of the FEECS, who published the results with colleagues in the journal Mathematics and Computers in Simulation.

The study opens new avenues in malware research and shows that fractal geometry can significantly improve their visualization and classification. "As the cybersecurity field evolves and new threats continue to emerge, similar interdisciplinary methods will be essential to stay ahead of these dangers. That's why we are continuing our research and, after dynamic analyses, we are also focusing on static ones, which are faster to detect dangerous viruses in practice," Zelinka explained.

But the methodology he developed based on dynamic analysis also has a number of benefits. This is because it also provides information on many details of malware behaviour in real time. "The method using dynamic analysis is important for further research so that experts can analyse and investigate the virus ex post. In addition, it has opened up a number of other interesting technical questions," added computer scientist and cyberneticist Zelinka.

Fractal geometry and fractals are used in many scientific fields, but many artists are also inspired by them. The Ostrava scientist does not count himself among artists, but he admits his fondness for art and fractals. "These are very beautiful patterns and I am happy when very abstract concepts, or in this case digital behaviour in cyberspace, can take on such a visual form. In this case, moreover, it is not an end in itself, but we have also gained an effective tool for the further development of cybersecurity," Zelinka concluded.