Project Articles

The 9th National Conference on Intelligent Information Processing（NCIIP 2023）

Default Latest Most Read

Please wait a minute... For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails Select Network security risk assessment method for CTCS based on α-cut triangular fuzzy number and attack tree Honglei YAO, Jiqiang LIU, Endong TONG, Wenjia NIU Journal of Computer Applications    2024, 44 (4): 1018-1026.   DOI: 10.11772/j.issn.1001-9081.2023050584 Abstract （164）   HTML （9）    PDF （2359KB）（126）       Knowledge map    Save To solve the problems of uncertain influence factors and indicator quantification difficulty in the risk assessment of industrial control networks， a method based on fuzzy theory and attack tree was proposed， and the proposed method was tested and verified on Chinese Train Control System （CTCS）. First， an attack tree model for CTCS was constructed based on network security threats and system vulnerability. α-cut Triangular Fuzzy Number （TFN） was used to calculate the interval probabilities of leaf nodes and attack paths. Then， Analytic Hierarchy Process （AHP） was adopted to establish the mathematical model for security event losses and get the final risk assessment result. Finally， the experimental result demonstrates that the proposed method implements system risk assessment effectively， predicts the attack paths successfully and reduces the influence of subjective factors. By taking advantage of the proposed method， the risk assessment result would be more realistic and provides reference and basis for the selection of security protection strategies. Table and Figures | Reference | Related Articles | Metrics Select Network abnormal traffic detection based on port attention and convolutional block attention module Bin XIAO, Yun GAN, Min WANG, Xingpeng ZHANG, Zhaoxing WANG Journal of Computer Applications    2024, 44 (4): 1027-1034.   DOI: 10.11772/j.issn.1001-9081.2023050649 Abstract （143）   HTML （10）    PDF （1692KB）（174）       Knowledge map    Save Network abnormal traffic detection is an important part of network security protection. At present， abnormal traffic detection methods based on deep learning treat the port number attribute the same as other traffic attributes， ignoring the importance of the port number. Considering the idea of attention， a novel abnormal traffic detection module based on Convolutional Neural Network （CNN） combining Port Attention Module （PAM） and Convolutional Block Attention Module （CBAM） was proposed to improve the performance of abnormal traffic detection. Firstly， the original network traffic was taken as the input of PAM， the port number attribute was separated and sent to the full connected layer， and the learned port attention weight value was obtained， and the traffic data after port attention was output by dot-multiplying with other traffic attributes. Then， the traffic data was converted into a grayscale map， and CNN and CBAM were used to extract the the channel and space information of the feature map more fully. Finally， the focus loss function was used to solve the problem of data imbalance. The proposed PAM has the advantages of few parameters， plug and play， and universal applicability. The accuracy of the proposed model is 99.18% for the binary-class classification task of abnormal traffic detection and 99.07% for the multi-class classification task on the CICIDS2017 dataset， and it also has a high recognition rate for classes with only a few training samples. Table and Figures | Reference | Related Articles | Metrics Select Device-to-device content sharing mechanism based on knowledge graph Xiaoyan ZHAO, Yan KUANG, Menghan WANG, Peiyan YUAN Journal of Computer Applications    2024, 44 (4): 995-1001.   DOI: 10.11772/j.issn.1001-9081.2023040500 Abstract （287）   HTML （58）    PDF （3288KB）（757）       Knowledge map    Save Device-to-Device（D2D） communication leverages the local computing and caching capabilities of the edge network to meet the demand for low-latency， energy-efficient content sharing among future mobile network users. The performance improvement of content sharing efficiency in edge networks not only depends on user social relationships， but also heavily relies on the characteristics of end devices， such as computation， storage， and residual energy resources. Therefore， a D2D content sharing mechanism was proposed to maximize energy efficiency with multidimensional association features of user-device-content， which took into account device heterogeneity， user sociality， and interest difference. Firstly， the multi-objective constraint problem about the user cost-benefit maximization was transformed into the optimal node selection and power control problem. And the multi-dimensional knowledge association features and the graph model for user-device-content were constructed by processing structurally multi-dimensional features related to devices， such as computing resources and storage resources. Then， the willingness measurement methods of users on device attributes and social attributes were studied， and a sharing willingness measurement method was proposed based on user socialization and device graphs. Finally， according to user sharing willingness， a D2D collaboration cluster oriented to content sharing was constructed， and a power control algorithm based on shared willingness for energy efficiency was designed to maximize the performance of network sharing. The experimental results on a real user device dataset and infocom06 dataset show that， compared to nearest selection algorithm and a selection algorithm without considering device willingness， the proposed power control algorithm based on shared willingness improves the system sum rate by about 97.2% and 11.1%， increases the user satisfaction by about 72.7% and 4.3%， and improves the energy efficiency by about 57.8% and 9.7%， respectively. This verifies the effectiveness of the proposed algorithm in terms of transmission rate， energy efficiency and user satisfaction. Table and Figures | Reference | Related Articles | Metrics Select Node coverage optimization of wireless sensor network based on multi-strategy improved butterfly optimization algorithm Xiuxi WEI, Maosong PENG, Huajuan HUANG Journal of Computer Applications    2024, 44 (4): 1009-1017.   DOI: 10.11772/j.issn.1001-9081.2023040501 Abstract （200）   HTML （20）    PDF （1855KB）（240）       Knowledge map    Save Aiming at the problems of low coverage rate and uneven distribution of nodes in Wireless Sensor Network （WSN）， a node coverage optimization strategy based on Multi-strategy Improved Butterfly Optimization Algorithm （MIBOA） was proposed. Firstly， the basic Butterfly Optimization Algorithm （BOA） was combined with Sparrow Search Algorithm （SSA） to improve the search process. Secondly， the adaptive weight coefficient was introduced to improve the optimization accuracy and convergence speed. Finally， the current best individual was perturbed by Cauchy mutation to improve the robustness of the algorithm. The optimization experiment results on benchmark functions show that， MIBOA can basically solve the optimal value of the test function within 3 seconds， and the average accuracy of convergence is improved by 97.96% compared with BOA. MIBOA was applied to the WSN node coverage optimization problem. Compared with optimization results of BOA and SSA， the node coverage rate was improved by 3.63 percentage points at least. Compared with the Improved Grey Wolf Optimization algorithm （IGWO）， the deployment time was shortened by 145.82 seconds. Compared with the Improved Whale Optimization Algorithm （IWOA）， the node coverage rate was increased by 0.20 percentage points and the time was shortened by 1 112.61 seconds. In conclusion， MIBOA can improve the node coverage rate and reduce the redundant coverage rate， and effectively prolong the lifetime of WSN. Table and Figures | Reference | Related Articles | Metrics Select Domain generalization method of phase-frequency fusion from independent perspective Bin XIAO, Mo YANG, Min WANG, Guangyuan QIN, Huan LI Journal of Computer Applications    2024, 44 (4): 1002-1009.   DOI: 10.11772/j.issn.1001-9081.2023050623 Abstract （258）   HTML （18）    PDF （2055KB）（282）       Knowledge map    Save The existing Domain Generalization （DG） methods process the domain features poorly and have weak generalization ability， thus a method based on the feature independence of the frequency domain was proposed to solve the domain generalization problem. Firstly， a frequency domain decomposition algorithm was designed to obtain domain-independent features from phase information by the Fast Fourier Transform （FFT） of depth features of the image， improving the recognition ability of domain-independent features. Secondly， from the independence perspective， the correlation of attributes in frequency domain features was further eliminated by weighting the features of samples， and the most effective domain-independent features were extracted to solve the poor generalization problem caused by correlation between sample features. Finally， the amplitude fusion strategy was proposed to narrow the distance between the source domain and the target domain， so as to further improve the generalization ability of the model to the unknown domain. Experimental results on popular image domain generalization datasets PACS and VLCS show that the average accuracy of the proposed method is 0.44， 0.59 percentage points higher than that of StableNet， and the proposed method achieves excellent performance on all datasets. Table and Figures | Reference | Related Articles | Metrics