Immune-genetic algorithm(IGA) with local search for intrusion detection system in computer network / Hamizan Suhaimi, Saiful Izwan Suliman, and Ismail Musirin

The Internet provides almost unlimited connectivity to the online world that is widely used in our daily lives nowadays. As for borderless connections, inventors have to face great challenges in providing the greatest quality of service specifically in terms of security. Even with existing security measures such as firewalls, Intrusion Detection System (IDS) and antivirus to protect the network, the network is still vulnerable and its resources can be compromised by third parties. This problem highlights the need to address network intrusion problems efficiently. By formulating a specific algorithm for this problem, the purpose of this study is to examine the performance of improvised Genetic Algorithms for network intrusion problems. Based on the 1999 KDD Cup data set with various disruptions simulated from the military network, this research was conducted based on this standard dataset. The performance in terms of average intrusion detection rate and false alarm rate of the proposed method and other available techniques were analyzed to evaluate and determine the best performance. The combination of Genetic Algorithm, Immune Algorithm and local search has produced good detection with acuracy rate of 98.91% and has the potential to be further investigated for other research areas.