In this paper, we report on experiments in which we used neural
networks for statistical anomaly intrusion detection systems. The five types of neural networks that we studied were: Perceptron; Backpropagation; Perceptron-Backpropagation-Hybrid; Fuzzy ARTMAP; and Radial-Based Function. We collected four separate data sets from different simulation scenarios, and these data sets were used to test various neural networks with different hidden neurons. Our results showed that the classification capabilities of BP and PBH outperform those of other neural networks.
Fuzzy min-max neural network (FMN), proposed by Simpson is a well-known supervised neuro-fuzzy classifier that has been successfully used by many researchers for pattern recognition. However, the FMN represents the learned knowledge with exhaustive details in a `fine-grained' manner that reduces its performance for pattern recognition in terms of the recall time per pattern. In this paper, we adapt the basic architecture of the FMN to represent the learned knowledge in a compact way that is in a `coarse-grained' manner, which is closed to human thinking. The working of the proposed method that is fuzzy min-max neural network with knowledge compaction (FMN-KC) is illustrated using the Fisher Iris dataset. The potential of using the FMN-KC for supervised outlier detection is demonstrated using a time-series disk defect dataset published by NASA and KDD cup 99 dataset available in UCI repository. The proposed method achieves around 50% gain in the recall time as compared to the original FMN and the recognition rate is also comparable. We strongly recommend using the proposed architecture FMN-KC for supervised outlier detection in the real time applications, where recall time per pattern is one of the key parameters.