The paper is devoted to the solution of the problem of identifying an intruder in a distributed automated system, which is not losing its relevance. It is proposed to investigate the data logged to build a profile of a legitimate user, and check in real-time whether his profile has changed dramatically. In case a critical deviation in the behavior of a legitimate user in an automated distributed environment has occurred, an alarm should be generated about a possible intrusion into the network by an intruder. Several approaches to solve the problem are considered. The first is a classical statistical method to construct a criterion for distinguishing random variables to detect deviation from standard user behavior using statistical models built on a class of strictly stable distributions. The second approach is based on numerical methods that use splines to approximate the observed value. The curves constructed with the help of third-order splines are selected as the boundaries of acceptable values of the estimated parameters for the legal user. The third approach is based without the methods developed for working with large-volume data and methods for clustering large-volume data, using a perceptron to find the boundary separating the legitimate user from the intruder. For all methods, the necessary number of observations required to build decisive rules of sufficient reliability is estimated. The probabilities of first- and second-order errors for the developed methods have been estimated.
Statistical Models for Intruder Detection in a Distributed Automated System
Lect. Notes in Networks, Syst.
International School on Neural Networks, Initiated by IIASS and EMFCSC ; 2022 ; St.Petersburg, Russia February 08, 2022 - February 10, 2022
Networked Control Systems for Connected and Automated Vehicles ; Kapitel : 104 ; 1025-1033
16.11.2022
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
INTRUDER DETECTION DEVICE, INTRUDER DETECTION METHOD, AND INTRUDER DETECTION PROGRAM
Europäisches Patentamt | 2024
|Fence vibrations [intruder detection]
IEEE | 2000
|Online Contents | 1997
British Library Online Contents | 1996
|British Library Online Contents | 1997