Authors Yu.A. Bryukhomitsky
Month, Year 12, 2013 @en
Index UDC 681.324
Abstract New approaches and principles of artificial immune system (AIS) building are considered, which differs from prior ones in that it reproduces the ability to adapt and self-organization that is appropriate to immune system of living organisms. There are new approaches to the property of double-plasticity modeling proposed, which based on the use of different mechanisms of detectors number formation and regulation. While the AIS operating, detectors are calibrated by the effectiveness of finding the "strangers". It also introduces a mechanism for regulating the balance of AIS capabilities to the discovery of new and previously encountered "strangers". At least, the AIS functioning get the properties of parametric and structural plasticity. The parametric plasticity is implemented on a pre-training stage and consists in selection of initial parameters for information processes representation and coding, realization of the templates creating procedure and creation of the primary set of detectors. The structural plasticity is implemented on the stage of active functioning in the "spirit of cooperation" by identifying and replacing the weakest elements by new ones, removing useless elements, filling the vacant niches, not occupied by the existing elements. Finally, in contrast to the well-known ones, AIS shows the complex functioning temper, inherent to living immune system: exogenous in protecting against external violators and endogenous in terms of ensuring of internal environment constancy and integrity and maintaining the mechanisms of internal communication.

Download PDF

Keywords Artificial immune system; adaptation; self-organization; detection of "strange" information processes; parametric and structural plasticity properties.
References 1. Искусственные иммунные системы и их применение / Под ред. Д. Дасгупты: Пер. с англ. / Под ред. А.А. Романюхи. – М.: Физматлит, 2006. – 344 с.
2. Bersini H., Varela F. Hints for adaptive problem solving gleaned from immune networks // Proc. 1st Conf. on Parallel Problem Solving from Nature (Eds. Ft.-P. Schwefel, R. Manner).
Springer-Verlag, 1990. – P. 343-354.
3. Bersini FI., Varela F. The immune learning mechanisms: Recruitment reinforcement and their applications // Computing with biological metaphors (Ed. R. Patton). L.: Chapman and Hall, 1994.
4. Detours V., Bersini H., Stewart J., Varela F. Development of an idiotypic network in shape space // J. Theor. Biol. – 1994. – Vol. 170. – P. 401-414.
5. Lundkvist I., Coutinho A., Varela F., Holmberg D. Evidence for a functional idiotypic network among natural antibodies in normal mice // Proc. Natl. Acad. Sci. – 1989. – Vol. 86. – P. 5074-5078.
6. Varela F., Coutinho A., Dupire B., Vaz N. Cognitive networks: Immune, neural and otherwise. In: Theoretical Immunology, V. 2 (Ed. A. Perelson). SFI Series on the Science of Complexity. New Jersey: Addison Wesley, – 1988. – P. 359-375.
7. Varela F.J., Coutinho A. Second generation immune network // Immunol. Today. – 1991. – Vol. 12, № 5. – P. 159-166.
8. Брюхомицкий Ю.А. Предпосылки создания моделей компьютерной безопасности на принципах функционирования иммунных систем // Известия ЮФУ. Технические науки. – 2012. – № 1 (126). – С. 159-165.
9. Брюхомицкий Ю.А. Модель искусственной иммунной системы с двойной пластичностью // Материалы ХIII Международной научно-практической конференции «Информационная безопасность». Ч. I. – Таганрог: Изд-во ЮФУ, 2013. – С. 147-155.
10. Брюхомицкий Ю.А. Регулирование распознающих свойств искусственных иммунных систем с двойной пластичностью // Материалы ХIII Международной научно-практической конференции «Информационная безопасность». Ч. I. – Таганрог: Изд-во ЮФУ, 2013. – С. 155-161.
11. Брюхомицкий Ю.А. Мониторинг информационных процессов методами искусственных иммунных систем // Известия ЮФУ. Технические науки. – 2012. – № 12 (137). – С. 82-90.
12. Васильев В.И. Интеллектуальные системы защиты информации: учебное пособие. – М.: Машиностроение, 2010. – 163 с.

Comments are closed.