The model retrieves software behavior information using a hierarchical model of nested auto-associating neural networks

Authors

  • Vitalii Martovytskyi Kharkiv National University of Radio Electronics, Ukraine
  • Ihor Ruban Kharkiv National University of Radio Electronics, Ukraine
  • Ihor Bukin Kharkiv National University of Radio Electronics, Ukraine
  • Lev Smyrnov Kharkiv National University of Radio Electronics, Ukraine

Abstract

The existing algorithms for searching for malicious code are imperfect. For the most part, search programs determine the presence of malicious code based on already known samples. Thus, as a part of the study, a model for extracting information from data was developed, containing hierarchically related basic elements based on deep noise-canceling auto-encoders. In addition, the requirements for the model and the necessary operation parameters were determined.

Published

2020-04-22

Issue

Section

DEVELOPMENT AND OPERATION OF COMPUTER AND INTELLECTUAL INFORMATION SYSTEMS