Authors:-G. S. Ubale
Abstract:-Intrusions in computer networks have driven the development of various techniques for intrusion detection systems (IDSs). Currently it is one of the most popular research topics in network security. IDS plays a vital role which try to keep safe our network from intruders. In general, the existing approaches seek two goals: high detection rate and low false rate. The problem with such proposed solutions is that they are usually processing intensive due to the large size of the training set in place. We propose a technique that combines an ant colony optimization algorithm with the well-known genetic algorithm to perform attack classification and detection. By adding these two algorithms we can efficiently managed to reduce the classification time substantially. The evaluation results show that our proposal is capable of detecting intrusions with high accuracy rates while keeping the computational cost low. We have examined the feasibility of our approach by conducting several experiments using the KDD dataset. It is therefore the goal of this paper to provide a comprehensive overview of the application of GAAPI to solve complex global continuous problems.
Full Issue
| View or download the full issue |