Abstract
Digital production integrates with all the areas of human activity including critical industries, therefore the task of detecting network attacks has a key priority in protecting digital manufacture systems. This article offers an approach for analysis of digital production security based on evaluation of a posteriori probability for change point in time-series, which are based on the change point coefficient values of digital wavelet-transform in the network traffic time-series. These time-series make it possible to consider the network traffic from several points of view at the same time, which plays an important role in the task of detecting network attacks. The attack methods vary significantly; therefore, in order to detect them it is necessary to monitor different values of various traffic parameters. The proposed method has demonstrated its efficiency in detecting network service denial attacks (SlowLoris and HTTP DoS) being realized at the application level.
Highlights
Digital production integrates with all the areas of human activity including critical industries, the task of detecting network attacks has a key priority in protecting digital manufacture systems
The key role in digital production is given to such technologies as artificial intelligence, sensor and cloud technologies aimed at supporting effective operation of complex industrial systems
Bearing in mind the large scale of these systems the task of mitigating the human factor effects on the operation of digital manufacture systems becomes relevant, because only machine intelligence is capable of processing large amounts of different data with high accuracy and extracting dependencies and properties that may go unnoticed for people
Summary
The modern level of science and equipment development is characterized by active transition from automated manufacture to digital manufacture practices. Incorrect operation of the systems in these industries may cause harm to people’s lives and health as well as bring the state significant financial losses [1] Resolving this problem is complicated by the following causes: big difference in types of digital manufacture system components caused by both technical difference of components by intended use and a great number of component manufacturers; low output capacity of most components; Intensive generation of large and diverse data volumes by digital manufacture systems; This high diversity of system components brings about a great number of generated data formats and different interfacing protocols to be applied and integrated. Even if they refer to the same class (for example, to service denial attack class) are carried out by intruders in a different way and to be detected it is necessary to monitor different characteristics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
