ИММУНОЛОГИЧЕСКАЯ МОДЕЛЬ КЛАВИАТУРНОГО МОНИТОРИНГА ОПЕРАТОРОВ ИНФОРМАЦИОННЫХ СИСТЕМ

Abstract

The purpose of this work is to develop a model of keyboard monitoring of information system operators,based on the use of a chain method of accounting keyboard handwriting parameters. The specifiedmethod provides estimation of operator's keyboard handwriting on chains of characters of givenlength, reflecting linguistically related parameters of keyboard set, characteristic for the given operator.The keyboard typing of such chains by the operator with "good" keyboard handwriting has significantlyhigher individuality due to correlation dependences between the time parameters of successive charactersand pauses. As a result, the chain method allows to provide higher accuracy of operator's identityverification. Keyboard monitoring based on the chain method is proposed to be implemented in thebasis of artificial immune systems using an immunological model of clonal selection, in which the detectorsare represented by identifying parameters of the distribution area of the keyboard parameters of"friend". In the tasks of keyboard monitoring the area of distribution of keyboard parameters of theverified operator is always significantly less than the cumulative area of distribution of keyboard parametersof other possible operators. The choice of the specified model allows to significantly reduce therequired volume of the detector population, and as a consequence - to significantly reduce the verificationtime of the working operator. The decision to replace "friend" operator with "stranger" is proposedto be considered reasonable when the frequency of operation of detectors exceeds the establishedthreshold value. The proposed immunological model has a number of advantages. The use of the chainmethod of keyboard parameters accounting allows to verify the operator with greater accuracy in comparisonwith traditional methods. The clonal selection model in combination with vector representationof the keyboard data allows to significantly speed up the learning process and reduce the time requiredto make a timely decision on the presence of a "stranger" operator. An important advantage of the modelis the ability to learn solely from the examples of keyboard handwriting operationally available"friend" operators. The use of the clonal selection model also makes it possible to significantly reducethe required volume of the population of detectors capable of effectively "covering" the distribution areaof the keyboard parameters of "friend" operator