Behavioural Biometrics Hardware Based on Bioinformatics Matching
- 669 Downloads
In this work we realized special hardware for intrusion detection systems (IDS) based on behavioural biometrics and using bionformatics’ Smith-Waterman algorithm. As far as we know there are no published hardware implementations of bioinformatics algorithms used for IDS. It is shown in the paper that the use of hardware can efficiently exploit the inherent parallelism of the algorithm and reach Gigabit data processing rates that are required for current communications. Each processing unit can be replicated many times on deployed Field Programmable Gate Array (FPGA) and depending on the capacity of the device, almost proportionally increase the throughput.
Keywordsbehavioural biometrics intrusion detection pattern recognition FPGA bioinformatics Smith-Waterman algorithm dynamic programming
Unable to display preview. Download preview PDF.
- 3.Coull, S., Branch, J., Szymanski, B., Breimer, E.: Intrusion Detection: A Bioinformatics Approach. In: Proc. 19th Annual Computer Security Applications Conf, p. 24 (2003)Google Scholar
- 6.Sai Krishna, V: Intrusion Detection Techniques: Pattern Matching and Protocol Analysis, Security Essentials (GSEC) Version 1.4b, April 26 (2003), http://www.giac.org/
- 7.Sinclair, C., Pierce, L., Matzner, S.: An Application of Machine Learning to Network Intrusion Detection. In: Proc. 1999 Anual Computer Security Applications Conf. (ACSAC), Phoenix, USA, December 1999, pp. 371–377 (1999)Google Scholar
- 9.Tripp, G.: An intrusion detection system for gigabit networks – architecture and an example system. Technical Report 7-04, Computing Laboratory, University of Kent (April 2004)Google Scholar
- 10.Underwood, K.D., Hemmert, K.S.: Closing the gap: CPU and FPGA trends in sustainable floating-point BLAS performance. In: Proc. 2004 IEEE Symposium on field-programmable custom computing machines (FCCM 2004), USA (2004)Google Scholar