The growing popularity of large language models in various fields of scientific and industrial activity leads to the emergence of solutions using these technologies for completely different tasks. This article suggests using the BERT, GPT, and GPT-2 language models to detect malicious code. The neural network model, previously trained on natural texts, is further trained on a preprocessed dataset containing program files with malicious and harmless code. The preprocessing of the dataset consists in the fact that program files in the form of machine instructions are translated into a textual description in a formalized language. The model trained in this way is used for the task of classifying software based on the indication of the content of malicious code in it. The article provides information about the conducted experiment on the use of the proposed model. The quality of this approach is evaluated in comparison with existing antivirus technologies. Ways to improve the characteristics of the model are also suggested.
Keywords: antivirus, neural network, language models, malicious code, machine learning, model training, fine tuning, BERT, GPT, GPT-2
The article describes the research of thermodurability of glass-carbon - one of the most promising carbon materials used in the production of luminophors and semiconductor materials, optical single crystals, etc. The aim of this work was to study the behavior glass-carbon in the course of thermo-cyclic testing. As a method of diagnostics of the birth and development of micro-cracks was used by the reception of signals of acoustic emission. It is shown that at heating in the samples glass-carbon there was a strong movement of dislocations in thermocyclic effects ,recognized in the signals of acoustic emission. As the number of pulses when heated above, than during the cooling of the sample, it is evidence of the accumulation of damages in the structure of the cyclic thermal processing glass-carbon samples. It is established, that the curves of the accumulation of defects at the pulses of acoustic emission, differ on the stage of heating and cooling. Proposed to use the curve of the aggregate accounts of acoustic emission pulses as a possible harbinger of destruction when heated glass-carbon of the product.
Keywords: acoustic emission, electrodeposition, the activity of the AE, the remote control.