MLS security policy evolution with genetic programming

ABSTRACT

In the early days a policy was a set of simple rules with a clear intuitive motivation that could be formalised to good effect. However the world is becoming much more complex. Subtle risk decisions may often need to be made and people are not always adept at expressing rationale for what they do. In this paper we investigate how policies can be inferred automatically using Genetic Programming (GP) from examples of decisions made. This allows us to discover a policy that may not formally have been documented, or else extract an underlying set of requirements by interpreting user decisions to posed "what if" scenarios. Three proof of concept experiments on MLS Bell-LaPadula, Budgetised MLS and Fuzzy MLS policies have been carried out. The results show this approach is promising.

REFERENCES

• 1: P. C. Cheng, P. Rohatgi, C. Keser, P. A. Karger, G. M. Wagner, and A. S. Reninger. Fuzzy Multi-Level Security: An Experiment on Quantified Risk-Adaptive Access Control. Technical report, IBM Research Report RC24190, 2007.
• 2: Pau-Chen Cheng , Pankaj Rohatgi , Claudia Keser , Paul A. Karger , Grant M. Wagner , Angela Schuett Reninger, Fuzzy Multi-Level Security: An Experiment on Quantified Risk-Adaptive Access Control, Proceedings of the 2007 IEEE Symposium on Security and Privacy, p.222-230, May 20-23, 2007 [doi>10.1109/SP.2007.21]
• 3: Horizontal Integration: Broader Access Models for Realizing Information Dominance. Technical Report JSR-04-132, The MITRE Corporation JASON Program Office, Mclean, Virginia, Dec 2004.
• 4: John R. Koza, Genetic programming: on the programming of computers by means of natural selection, MIT Press, Cambridge, MA, 1992
• 5: S. Luke. ECJ version 16 A Java-based Evolutionary Computation Research System, August 2007.
• 6: P. D. McDaniel. Policy Evolution: Autonomic Environmental Security, December 2004.
• 7: R. R. F. Mendes, F. de B. Voznika, J. C. Nievola, and A. A. Freitas. Discovering Fuzzy Classification Rules with Genetic Programming and Co-Evolution. In L. Spector, E. D. Goodman, A. Wu, W. B. Langdon, H.-M. Voigt, M. Gen, S. Sen, M. Dorigo, S. Pezeshk, M. H. Garzon, and E. Burke, editors, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001), page 183, San Francisco, California, USA, 7--11 2001. Morgan Kaufmann.
• 8: David J. Montana, Strongly typed genetic programming, Evolutionary Computation, v.3 n.2, p.199-230, Summer 1995 [doi>10.1162/evco.1995.3.2.199]
• 9: G. Pappa and A. Freitas. Towards a genetic programming algorithm for automatically evolving rule induction algorithms. In J. Furnkranz, editor, Proc. ECML/PKDD-2004 Workshop on Advances in Inductive Learning, pages 93--108, Pisa, Italy, September 2004.
• 10: Man Leung Wong , Kwong Sak Leung, Data Mining Using Grammar-Based Genetic Programming and Applications, Kluwer Academic Publishers, Norwell, MA, 2000

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Induction

Additional Classification:
  D. Software
  D.4 OPERATING SYSTEMS
      D.4.6 Security and Protection
          Subjects: Access controls

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems

General Terms:
Experimentation

Keywords:
MLS, genetic programming, policy inference, security policy