Neural Networks for Intrusion Detection Systems

Intrusion detection systems have got the potential to provide the first line of defense against computer network attacks. However, this potential is far from being exploited considering the fact that most of commercial IDS in the market do not identify novel attacks and generate false alerts for legitimate user activities. They mainly deploy misuse detection and are fully dependant on human interaction. Neural networks can be applied successfully to tackle these issues and design better intrusion detection system. Neural networks have already been used to solve many problems related to pattern recognition, data mining, data compression and research is still underway with regards to intrusion detection systems. Unsupervised learning and fast network convergence are some features that can be integrated in the newly designed IDS system using neural networks. This study will aim to explore current applications of neural networks for intrusion detection systems and identify possible neural network algorithms suitable for the task in hand.