The accuracy of historical situation values is required for traditional network security situation prediction(NSSP).There are discrepancies in the correlation and weighting of the various network security elements.To ...The accuracy of historical situation values is required for traditional network security situation prediction(NSSP).There are discrepancies in the correlation and weighting of the various network security elements.To solve these problems,a combined prediction model based on the temporal convolution attention network(TCAN)and bi-directional gate recurrent unit(BiGRU)network is proposed,which is optimized by singular spectrum analysis(SSA)and improved quantum particle swarmoptimization algorithm(IQPSO).This model first decomposes and reconstructs network security situation data into a series of subsequences by SSA to remove the noise from the data.Furthermore,a prediction model of TCAN-BiGRU is established respectively for each subsequence.TCAN uses the TCN to extract features from the network security situation data and the improved channel attention mechanism(CAM)to extract important feature information from TCN.BiGRU learns the before-after status of situation data to extract more feature information from sequences for prediction.Besides,IQPSO is proposed to optimize the hyperparameters of BiGRU.Finally,the prediction results of the subsequence are superimposed to obtain the final predicted value.On the one hand,IQPSO compares with other optimization algorithms in the experiment,whose performance can find the optimum value of the benchmark function many times,showing that IQPSO performs better.On the other hand,the established prediction model compares with the traditional prediction methods through the simulation experiment,whose coefficient of determination is up to 0.999 on both sets,indicating that the combined prediction model established has higher prediction accuracy.展开更多
The Internet of Things(IoT)system has confronted dramatic growth in high dimensionality and data traffic.The system named intrusion detection systems(IDS)is broadly utilized for the enhancement of security posture in ...The Internet of Things(IoT)system has confronted dramatic growth in high dimensionality and data traffic.The system named intrusion detection systems(IDS)is broadly utilized for the enhancement of security posture in an IT infrastructure.An IDS is a practical and suitable method for assuring network security and identifying attacks by protecting it from intrusive hackers.Nowadays,machine learning(ML)-related techniques were used for detecting intrusion in IoTs IDSs.But,the IoT IDS mechanism faces significant challenges because of physical and functional diversity.Such IoT features use every attribute and feature for IDS self-protection unrealistic and difficult.This study develops a Modified Metaheuristics with Weighted Majority Voting Ensemble Deep Learning(MM-WMVEDL)model for IDS.The proposed MM-WMVEDL technique aims to discriminate distinct kinds of attacks in the IoT environment.To attain this,the presented MM-WMVEDL technique implements min-max normalization to scale the input dataset.For feature selection purposes,the MM-WMVEDL technique exploits the Harris hawk optimization-based elite fractional derivative mutation(HHO-EFDM)technique.In the presented MM-WMVEDL technique,a Bi-directional long short-term memory(BiLSTM),extreme learning machine(ELM)and an ensemble of gated recurrent unit(GRU)models take place.A wide range of simulation analyses was performed on CICIDS-2017 dataset to exhibit the promising performance of the MM-WMVEDL technique.The comparison study pointed out the supremacy of the MM-WMVEDL method over other recent methods with accuracy of 99.67%.展开更多
基金This work is supported by the National Science Foundation of China(61806219,61703426,and 61876189)by National Science Foundation of Shaanxi Provence(2021JM-226)by the Young Talent fund of the University,and the Association for Science and Technology in Shaanxi,China(20190108,20220106)by and the Innovation Capability Support Plan of Shaanxi,China(2020KJXX-065).
文摘The accuracy of historical situation values is required for traditional network security situation prediction(NSSP).There are discrepancies in the correlation and weighting of the various network security elements.To solve these problems,a combined prediction model based on the temporal convolution attention network(TCAN)and bi-directional gate recurrent unit(BiGRU)network is proposed,which is optimized by singular spectrum analysis(SSA)and improved quantum particle swarmoptimization algorithm(IQPSO).This model first decomposes and reconstructs network security situation data into a series of subsequences by SSA to remove the noise from the data.Furthermore,a prediction model of TCAN-BiGRU is established respectively for each subsequence.TCAN uses the TCN to extract features from the network security situation data and the improved channel attention mechanism(CAM)to extract important feature information from TCN.BiGRU learns the before-after status of situation data to extract more feature information from sequences for prediction.Besides,IQPSO is proposed to optimize the hyperparameters of BiGRU.Finally,the prediction results of the subsequence are superimposed to obtain the final predicted value.On the one hand,IQPSO compares with other optimization algorithms in the experiment,whose performance can find the optimum value of the benchmark function many times,showing that IQPSO performs better.On the other hand,the established prediction model compares with the traditional prediction methods through the simulation experiment,whose coefficient of determination is up to 0.999 on both sets,indicating that the combined prediction model established has higher prediction accuracy.
基金funded by Institutional Fund Projects under Grant No.(IFPIP:667-612-1443).
文摘The Internet of Things(IoT)system has confronted dramatic growth in high dimensionality and data traffic.The system named intrusion detection systems(IDS)is broadly utilized for the enhancement of security posture in an IT infrastructure.An IDS is a practical and suitable method for assuring network security and identifying attacks by protecting it from intrusive hackers.Nowadays,machine learning(ML)-related techniques were used for detecting intrusion in IoTs IDSs.But,the IoT IDS mechanism faces significant challenges because of physical and functional diversity.Such IoT features use every attribute and feature for IDS self-protection unrealistic and difficult.This study develops a Modified Metaheuristics with Weighted Majority Voting Ensemble Deep Learning(MM-WMVEDL)model for IDS.The proposed MM-WMVEDL technique aims to discriminate distinct kinds of attacks in the IoT environment.To attain this,the presented MM-WMVEDL technique implements min-max normalization to scale the input dataset.For feature selection purposes,the MM-WMVEDL technique exploits the Harris hawk optimization-based elite fractional derivative mutation(HHO-EFDM)technique.In the presented MM-WMVEDL technique,a Bi-directional long short-term memory(BiLSTM),extreme learning machine(ELM)and an ensemble of gated recurrent unit(GRU)models take place.A wide range of simulation analyses was performed on CICIDS-2017 dataset to exhibit the promising performance of the MM-WMVEDL technique.The comparison study pointed out the supremacy of the MM-WMVEDL method over other recent methods with accuracy of 99.67%.
