A Distributed and Hierarchical Diagnostic Model for Tolerance to Result Manipulation Attacks in Computational Grids

• Felipe Martins UFC
• Rossana M. de Castro Andrade UFC
• Aldri L. dos Santos UFC
• José Neuman de Sousa UFC

Abstract

Grid applications are susceptible to manipulation attacks, since nodes can act in a malicious way, corrupting the jobs results. In order to avoid that grid users obtain uncorrected results, this paper presents a diagnosis model for verifying integrity of the jobs processing in computational grids. The model establishes a hierarchy among the nodes, in accordance to the historical behavior of the nodes in the environment. A new security layer is implemented in a grid simulator in order to validate this strategy. The results testify the effectiveness of the model using scenarios with different quotas of malicious nodes, providing a rate of 100% detection and 99,7% accuracy of processed jobs.

References

A. Setiawan, D. Adiutama, J. Liman, A. Luther, and R. Buyya. Gridcrypt: High performance symmetric key cryptography using enterprise grids. In PDCAT 2004: Parallel and Distributed Computing - Applications and Technologies, pages 872–877, 2004.

E. P. Duarte and T. Nanya. A hierarchical adaptive distributed system-level diagnosis algorithm. In IEEE Transactions on Computers, volume 47, pages 34–45. IEEE Computer Society, 1998.

M. Hollick. On the effect of node misbehavior in ad hoc networksv. In Proceedings of IEEE International Conference on Communications (ICC 2004), volume 6, pages 3759–3763, 2004.

F. Preparata, G. Metze, and R. Chien. On the connection assignment problem of diagnosable systems. IEEE Transactions on Electronic Computers, 16:848–854, 1968.

R. P. Bianchini Jr. and R. W. Buskens. Implementation of online distributed system-level diagnosis theory. IEEE Transactions on Computers, 41(5):616–626, 1992.

J. Maeng and M. Malek. A comparison connection assignment for self-diagnosis of multiprocessor systems. In Digest 11th International Symposium Fault Tolerant Computing, pages 173–175, 1981.

F. Martins, M. Maia, R. M. de Castro Andrade, A. Luiz dos Santos, and J. Neuman de Souza. Detecting malicious manipulation in grid environments. In SBAC-PAD - 18th International Symposium on Computer Architecture and High Performance Computing, pages 28–35. IEEE Computer Society, 2006.

R. Buyya and M. Murshed. Gridsim: A toolkit for the modeling and simulation of distributed resource management and scheduling for grid computing. In Journal of Concurrency and Computation: Practice and Experience (CCPE), 2002.