Research On Intrusion Detection Based On Deep Neural Network

With the rapid development of 5G,Cloud computing,Internet of things and other network technologies,security protection technology is constantly updated.However,there are large and complex attacks in the network.The massive data generated by the network has brought great difficulties to network security,and also means challenges.These attacks have become one of the main threats to the network and information security.The main work of this paper is as follows:(1)In view of the shortcomings of traditional BP neural network used in intrusion detection,BP neural network model is prone to fall into local optimal,slow convergence speed and large randomness of initial value.In this paper,we propose an improved algorithm called beetle swarm Optimization(BSO)is used to optimize the weight and threshold of BP neural network,and two ways of learning are used to enhance the algorithm'ability to jump out of local optimization by using variable perceptual factors and guidance learning strategies,and then realize the goal of improving the global optimization ability of the algorithm.The paper also uses the characteristics of swarm intelligence of tianniu algorithm to solve the problem of slow convergence of BP neural network.Finally,BSO BP neural network model is established to be applied in intrusion detection.The simulation results show that the optimized BP neural network model can significantly improve the performance of the model,including improving the convergence rate,detecting the intrusion data and reducing the false alarm rate.(2)In view of the advantages of deep neural network in the field of intrusion detection.In order to further improve the detection accuracy and performance,we proposed an intrusion detection model based on improved deep belief network(DBN).Traditional neural network training methods,like Back Propagation(BP),start to train a model with preset parameters such as the randomly initialized weights and thresholds,which may bring some issues,e.g.,attracting the model to the local optimal solutions,or requiring a long training period.We use the Kernel-based Extreme Learning Machine(KELM)with the supervised learning ability to replace the BP algorithm in DBN in a bid to ameliorate the situation.Considering the problem of poor classification performance usually caused by randomly initializing kernel parameters with KELM,an enhanced grey wolf optimizer(EGWO)is designed to optimize the parameters of KELM.In order to improve the search ability and optimization ability of the traditional grey wolf optimizer algorithm,a novel optimization strategy combining the inner and outer hunting is introduced.Experiments on KDDCup99,NSL-KDD,UNSW-NB15 and CICIDS2017 datasets show that the proposed DBN-EGWO-KELM algorithm has greater advantages in terms of its accuracy,precision,true positive rate,false positive rate and other evaluation indices compared with BP,RBF,SVM,KELM,LIBSVM,CNN,DBN-KELM and other intrusion detection models,and can effectively meet the requirements of intrusion detection of complex networks.