Intrusion Detection Algorithm of EPSO Combined with BP Neural Network

Aiming at the problems of large number of weights and thresholds of back propagation neural network (BPNN), a novel back propagation neural network integrated with particle swarm optimization based on entropy model (EPSO-BPNN) is proposed to improve the optimization effect of weights and thresholds for intrusion detection algorithm. Firstly, the entropy model was introduced to obtain the search characteristics of particle swarm optimization (PSO) algorithm. Then, the entropy value was used to increase the inertia weight timely. Furthermore, the optimal particle was decoded as the weights and thresholds obtained by particle swarm optimization based on entropy model (EPSO) algorithm. They are further optimized in the training phase. The experimental results show that EPSO-BPNN algorithm has a higher solution accuracy and convergence rate than PSO-BPNN algorithm in entropy value, fitness value and mean square error. The intrusion detection rate of EPSO-BPNN algorithm is 92.90%, and it has better intrusion detection rate on five network data types.

[1]  Seyed Mojtaba Hosseini Bamakan,et al.  A New Intrusion Detection Approach Using PSO based Multiple Criteria Linear Programming , 2015, ITQM.

[2]  A. M. Viswa Bharathy,et al.  A multi-class classification MCLP model with particle swarm optimization for network intrusion detection , 2017 .

[3]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[4]  Farrukh Aslam Khan,et al.  A hybrid technique using binary particle swarm optimization and decision tree pruning for network intrusion detection , 2018, Cluster Computing.

[5]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[6]  Iraj Mahdavi,et al.  Anomaly network-based intrusion detection system using a reliable hybrid artificial bee colony and AdaBoost algorithms , 2019, J. King Saud Univ. Comput. Inf. Sci..

[7]  Alyani Ismail,et al.  A New Intrusion Detection System Based on Fast Learning Network and Particle Swarm Optimization , 2018, IEEE Access.

[8]  Rosni Abdullah,et al.  Intrusion detection system based on a modified binary grey wolf optimisation , 2019, Neural Computing and Applications.

[9]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[10]  Said Fathy El-Zoghdy,et al.  A Neural Network-Based Learning Algorithm for Intrusion Detection Systems , 2017, Wirel. Pers. Commun..

[11]  Dorothy E. Denning,et al.  An Intrusion-Detection Model , 1987, IEEE Transactions on Software Engineering.

[12]  Kocsis Zoltán Tamás,et al.  IEEE World Congress on Computational Intelligence , 2019, IEEE Computational Intelligence Magazine.