Information Technology Reference
In-Depth Information
The input is any vector
Z
of the network connection record (see central dialog box
in Fig. 1). The emulator computes its binding energies with 5th
and 6th right singular
vectors and map the vector
Z
to a point
P={w
1
,w
2
}
in 2D shape space (see bold un-
numbered cross in both screens of the emulator). Then the emulator determines the
closest steady B-cell in left-hand screen, and thus, recognizes normal behavior (by the
classes 6, 7) or intrusion (by the other classes).
The test of 106 input records gave 4 “false positives” but none “false negative”.
The last result is more important, because none of intrusion (“non-self”) was detected
as 'normal' (“self”) connection. Besides, 4 normal connections corresponded to false
positive might be treated as dangerous, because their behavior looks similar to defi-
nite types of intrusions.
Acknowledgements
This work is supported by the European Commission under the project IST-2000-
26016 “Immunocomputing”. A. Tarakanov acknowledges also the support of EOARD
under the ISTC project 2200p “Development of mathematical models of immune
networks intended for information security assurance”. The authors would like to
thank Sergey Kvachev for his help in software implementation of the model.
References
1. Bay, S.D.: The UCI KDD Archive [http://kdd.ics.uci.edu]. Irvine, CA: University of Cali-
fornia, Dept. of Information and Computer Science (1999)
2. Dasgupta, D. (ed.): Artificial Immune Systems and Their Applications. Springer, Berlin
(1999)
3. De Boer, R.J., Segel, L.A., Perelson, A.S.: Pattern formation in one and two-dimensional
shape space models of the immune system. J. Theoret. Biol. 155 (1992) 295-333
4. De Castro, L.N., Timmis, J. Artificial Immune Systems: A New Computational Intelligence
Paradigm. Springer, New York (2002)
5. Gutnikov, S, Melnikov, Yu.: A simple non-linear model of immune response. Chaos, Soli-
tons, and Fractals, 16 (2003) 125
6. Horn, R., Johnson, Ch.: Matrix Analysis. Cambridge University Press (1986)
7. Jerne, N.K.: Toward a network theory of the immune system. Ann. Immunol. 125C Paris
(1974) 373-389
8. Tarakanov, A.O.: Information security with formal immune networks. Lecture Notes in
Computer Science, Vol. 2052. Springer, Berlin (2001) 115-126
9. Tarakanov, A., Adamatzky, A.: Virtual clothing in hybrid cellular automata. Kybernetes
(Int. J. of Systems & Cybernetics) 31 (7/8) (2002) 1059-1072
10. Tarakanov, A., Dasgupta, D.: An immunochip architecture and its emulation. NASA/DoD
Conf. on Evolvable Hardware EH-2002. Alexandria, Virginia (2002) 261-265
11. Tarakanov, A.O., Skormin, V.A., Sokolova, S.P.: Immunocomputing: Principles and Ap-
plications. Springer, New York (2003, in press)
