Abstract:
Over the past several years, the Internet environment has become more complex and untrusted. Enterprise networked systems are inevitably exposed to the increasing threats posed by hackers as well as malicious users internal to a network. IDS technology is one of the important tools used now-a-days, to counter such threats. The goal of intrusion detection is to identify unauthorized use, misuse and abuse of computer system insiders and outsiders penetrators. Various IDS techniques has been proposed, which identifies and alarms for such threats or attacks.
The thesis proposes design and implement an intrusion detection system based on Artificial neural network to provide the potential and classify network activity based on KDD dataset. The performance of the classification algorithms was evaluated by computing the percentages of Sensitivity(SE), Specificity(SP), Accuracy(AC) and Mathews Correlation Coefficient(MCC). It was found that the system is capable of detecting with a sensitivity of 83.1% and the accuracy is about 75%. Results show system that can detect new types of attacks with fairly accurate results.
