Algorithm for identifying threats to information security in distributed multiservice networks of government bodies

The results of studies are presented, the purpose which was to develop an algorithm for identifying information security threats in distributed multiservice networks that provide interaction regional government bodies, as well their communication with population region. relevance research topic is due a significant increase various types cyber attacks on computer public authorities and need level these by intellectualizing methods combating threats. based use machine learning analyze incoming traffic order identify events affect state authorities. provides input preprocessing, result set images (signatures) obtained from Wasm binary files formed, then image classifier launched. It contains sequential inclusion deep neural – convolutional network signature classification recurrent processes sequences at output network. Features formation signatures proposed algorithm, network, make it possible obtain resulting assessment security, taking into account history its current state. aggregated comparing actual those available database. aggregation performed fuzzy inference system second type, using implication according Mamdani generates final Software developed implements experiments were carried out synthetic data set, showed efficiency confirmed feasibility further improvement.