An Optimization Method for Intrusion Detection Classification Model Based on Deep Belief Network

Abstract

The rapid development and popularization of the network have brought many problems to network security. Intrusion detection technology is often used as an effective security technology to protect the network. The deep belief network (DBN), as a classic model of deep learning, has good classification performance and is often used in the field of intrusion detection. However, the network structure of DBN is generally set through practical experience. For the optimization problem of the DBN-based intrusion detection classification model (DBN-IDS), this paper proposes a new joint optimization algorithm to optimize the DBN's network structure. First, we design a particle swarm optimization (PSO) based on the adaptive inertia weight and learning factor. Second, we use the fish swarm behavior of cluster, foraging, and other behaviors to optimize the PSO to find the initial optimization solution. Then, based on the initial optimization solution, we use the genetic operators with self-adjusting crossover probability and mutation probability to optimize the PSO to search the global optimization solution. Finally, the global optimization solution constructed by the above-mentioned joint optimization algorithm is used as the network structure of the intrusion detection classification model. The experimental results show that compared with other DBN-IDS optimization algorithms, our algorithm shortens the average detection time by at least 24.69% on the premise of increasing the average training time by 6.9%; compared with the tested classification algorithms, our DBN-IDS improves the average classification accuracy by at least 1.3% and up to 14.80% in the five-category classification, which is proved to be an efficient DBN-IDS optimization method. INDEX TERMS Intrusion detection, deep belief network, particle swarm optimization, artificial fish swarm algorithm, genetic algorithm.

Network intrusion detection system: A systematic study of machine learning and deep learning approaches

“…To improve the detection accuracy of IDS, Wei et al 121 proposed a DL‐based model DBN, which is optimized by combining the particle swarm, fish swarm, and genetic algorithms. The model was tested using the NSL‐KDD dataset.…”

Integration of recurrent convolutional neural network and optimal encryption scheme for intrusion detection with secure data storage in the cloud

“…The intrusion prediction performance of proposed attention-based RCNN is compared with different state-of-art methods such as ANN, 19 PSO, 22 HGGWO, 23 and DBN-IDS. 24 When compared with all other existing algorithms, the proposed work delivers betters and optimal performance outputs in terms of specificity, accuracy, and sensitivity. Therefore, the intrusion detection performance compared with existing methods is discussed in Table 2.…”

“…However, this approach has an increased runtime issue. Wei et al 24 proposed a deep belief network (DBN)-based IDS to classify the intrusion in the network. To overcome the structure optimization problem that exists in the DBN, they created a joint optimizing technique combining three algorithms namely PSO, artificial fish swarm optimization (AFSO), and genetic algorithm (GA).…”

A Novel Wireless Network Intrusion Detection Method Based on Adaptive Synthetic Sampling and an Improved Convolutional Neural Network

“…The BAT model uses an attention mechanism to filter the network flow vectors generated by the BLSTM model to obtain the key characteristics of network traffic classification. Wei et al [32] applied particle swarm optimization (PSO) to optimize the structure of DBN, and the improved DBN achieves significant anomaly detection ability.Gao et al [33] designed an effective attack recognition method by combining association rules and improved deep neural networks (DNN), which uses the apriori algorithm to mine the association between discrete features and labels to improve the recognition accuracy. Yin et al [20] presented an effective attack recognition model by using feature enhancement and improved RNN; however, the feature enhancement method also increases the computational complexity of the model.…”