To search, Click below search items.


All Published Papers Search Service


Mining network traffics for intrusion detection based on Bagging ensemble Multilayer perceptron with Genetic algorithm optimization


Mehdi Moukhafi, Khalid El Yassini and Seddik Bri


Vol. 18  No. 5  pp. 59-66


Due to the frequency of malicious network activities and network policy violations, Intrusion Detection Systems (IDS) have become a necessity in computer security systems because of the increase in unauthorized accesses and attacks. Current IDSs are mainly based on techniques built on heuristic rules called signatures to detect intrusions in a network environment. These approaches based signature could only detect known attacks and referenced above. Since there is no signature for new attacks, other approaches must be taken in consideration, such as algorithms learning machine to detect a known and unknown attacks. Recent researches suggest combining multiple classifiers could have a better performance. In this paper, we propose a method of intrusion detection based on a combination of GA(Genetic algorithm) and Bagging ensemble MLP (Multilayer Perceptron) Neural Network to develop a model for intrusion detection system. The performance of the proposed method of intrusion detection was evaluated on all NSL-KDD test set and NSL-KDD train set is used for training the GA-Bagging-MLP model. Additionally, the performance of this approach has been analysed and compared with a number of existing approaches tested in the same data set. The results show that proposed method outperforms the existing approaches.


Machine learning Based Intrusion Detection Parameters optimization Genetic algorithm Multilayer perceptron Neural Network