Menyu
ITI
əməkdaslarının elmi isləri
Elektron kitabxana
Konfranslar İnformasiya Sistemi
Qəzetlər
UOT 004
|
ITI əməkdaşlarının elmi işləri - məqalə |
Biblioqrafik təsvir | Alguliyev , R.M. Radon transform based malware classification in cyber-physical system using deep learning / R.M. Alguliyev , R.M. Aliguliyev , L.V. Sukhostat // Results in Control and Optimization. - 2024. - N: Vol.14, issue 100382.- P. 1-14. | Annotasiya | The development of cyber-physical systems entails the growth and diversity of malware, which
increases the scale of cybersecurity threats. Attackers use malicious software to compromise
various components of cyber-physical systems. Existing technologies make it possible to reduce
the risk of malware infection using vulnerability and intrusion scanners, network analyzers, and
other tools. However, there is no perfect protection against the increasingly sophisticated types of
malware. The goal of this research is to solve this problem by combining different visual representations of malware and detection models based on transfer learning. This method considers
two pre-trained deep neural network models (AlexNet and MobileNet) that are capable of
differentiating various malware families using grayscale images. Radon transform is applied to
the resulting grayscale malware images to improve the classification accuracy of the new malware
binaries. The proposed model is evaluated using three datasets (Microsoft Malware Classification,
IoT_Malware and MalNet-Image datasets). The results show the superiority of the proposed model
based on transfer learning over other methods in terms of the efficiency of classifying malware
families aimed at infecting cyber-physical systems. | Elektron variant | Elektron variant |
|
________
© ict.az http://ict.az/az
|
|