似然多元分类的动态恶意节点检测算法
|
摘要
针对无线传感器网络中恶意节点的检测识别问题,提出一种似然多元分类的无线传感器网络动态恶意节点检测算法。分析恶意节点的异常状态信息,提取恶意节点的特征属性;对恶意节点的攻击模式进行建模,结合似然多元分类算法和贝叶斯规则求出节点类型划分的最终判别函数。实验结果表明,相比移动恶意攻击节点分布式检测方案和基于重复博弈的恶意节点检测算法,该算法在检测和识别恶意节点上具有更高的准确度和更低的平均检测错误率。
To solve the problems of detection and identification of malicious nodes in wireless sensor networks,a dynamic malicious node detection algorithm based on likelihood multivariate classification in wireless sensor network was proposed.The abnormal state information of malicious nodes was analyzed to extract feature attributes of malicious nodes.Attack modeling of malicious nodes was modeled,and the likelihood multivariate classification algorithms and Bayes' rule were combined to find final discriminant function of node classification.Simulation results show that compared with mobile malicious attacks nodes distributed detection scheme and malicious node detection algorithm based on repeated games,the proposed method has higher accuracy and lower average detection error rate in detection and identification of malicious nodes.
To solve the problems of detection and identification of malicious nodes in wireless sensor networks,a dynamic malicious node detection algorithm based on likelihood multivariate classification in wireless sensor network was proposed.The abnormal state information of malicious nodes was analyzed to extract feature attributes of malicious nodes.Attack modeling of malicious nodes was modeled,and the likelihood multivariate classification algorithms and Bayes' rule were combined to find final discriminant function of node classification.Simulation results show that compared with mobile malicious attacks nodes distributed detection scheme and malicious node detection algorithm based on repeated games,the proposed method has higher accuracy and lower average detection error rate in detection and identification of malicious nodes.
引文
[1]Chen M.Reconfiguration of sustainable thermoelectric generation using wireless sensor network[J].IEEE Transactions on Industrial Electronics,2014,61(6):2776-2783.
[2]Leu JS,Chiang TH,Yu MC,et al.Energy efficient clustering scheme for prolonging the lifetime of wireless sensor network with isolated nodes[J].IEEE Communications Letters,2015,19(2):259-262.
[3]Yang F,Wang KC,Huang Y.Energy-neutral communication protocol for very low power microbial fuel cell based wireless sensor network[J].IEEE Sensors Journal,2015,15(4):2306-2315.
[4]Serdaroglu KC,Baydere S.WiSEGATE:Wireless sensor network gateway framework for internet of things[J].Wireless Networks,2015,23(1):1-17.
[5]Lee S,Younis M,Lee M.Connectivity restoration in a partitioned wireless sensor network with assured fault tolerance[J].Ad Hoc Networks,2015,24(PA):1-19.
[6]Wang J,Dong W,Cao Z,et al.On the delay performance in a large-scale wireless sensor network:Measurement,analysis,and implications[J].IEEE/ACM Transactions on Networking,2015,23(1):186-197.
[7]Wang YC.A Two-phase dispatch heuristic to schedule the movement of multi-attribute mobile sensors in a hybrid wireless sensor network[J].IEEE Transactions on Mobile Computing,2014,13(4):709-722.
[8]ZHANG Lin,YIN Na,WANG Ruchuan.Research on malicious node identification based on DPAM-MD algorithm in wireless sensor networks[J].Journal of Communications,2015,36(S1):1-7(in Chinese).[张琳,尹娜,王汝传.无线传感网中基于DPAM-MD算法的恶意节点识别研究[J].通信学报,2015,36(S1):1-7.]
[9]CAI Shaobin,HAN Qilong,GAO Zhenguo,et al.Research on cloud based sensor node identification technology in wireless sensor network[J].Acta Electronica Sinica,2012,40(11):2232-2238(in Chinese).[蔡绍滨,韩启龙,高振国,等.基于云模型的无线传感器网络恶意节点识别技术的研究[J].电子学报,2012,40(11):2232-2238.]
[10]TONG Weiming,LIANG Jianquan,LU Lei,et al.Intrusion detection scheme based node trust value in WSNs[J].Systems Engineering and Electronics,2015,37(7):1644-1649(in Chinese).[佟为明,梁建权,卢雷,等.基于节点信任值的WSNs入侵检测方案[J].系统工程与电子技术,2015,37(7):1644-1649.]
[11]Ho JW,Wright M,Das SK.Distributed detection of mobile malicious node attacks in wireless sensor networks[J].Ad Hoc Networks,2012,10(3):512-523.
[12]Ning YU,Wan J.Repeated game based localization algorithm for wireless sensor networks with malicious beacon nodes[J].Ad Hoc&Sensor Wireless Networks,2015,25(1):45-68.
[13]Cuadros-Rodríguez L,Pérez-Casta1o E, Ruiz-Samblás C.Quality performance metrics in multivariate classification methods for qualitative analysis[J].Trac Trends in Analytical Chemistry,2016,80(1):612-624.
[14]Kim H.Best linear classification rule for multivariate interval screened data[J].Communications in Statistics-Theory and Methods,2015,44(8):1669-1690.
[15]Zhou PY,Chan KCC.A feature extraction method for multivariate time series classification using temporal patterns[C]//PAKDD,2015:409-421.
[16]Dai H,Liu H,Jia Z.Dynamic malicious node detection with semi-supervised multivariate classification in cognitive wireless sensor networks[J].Concurrency&Computation Practice&Experience,2015,27(12):2910-2923.
[2]Leu JS,Chiang TH,Yu MC,et al.Energy efficient clustering scheme for prolonging the lifetime of wireless sensor network with isolated nodes[J].IEEE Communications Letters,2015,19(2):259-262.
[3]Yang F,Wang KC,Huang Y.Energy-neutral communication protocol for very low power microbial fuel cell based wireless sensor network[J].IEEE Sensors Journal,2015,15(4):2306-2315.
[4]Serdaroglu KC,Baydere S.WiSEGATE:Wireless sensor network gateway framework for internet of things[J].Wireless Networks,2015,23(1):1-17.
[5]Lee S,Younis M,Lee M.Connectivity restoration in a partitioned wireless sensor network with assured fault tolerance[J].Ad Hoc Networks,2015,24(PA):1-19.
[6]Wang J,Dong W,Cao Z,et al.On the delay performance in a large-scale wireless sensor network:Measurement,analysis,and implications[J].IEEE/ACM Transactions on Networking,2015,23(1):186-197.
[7]Wang YC.A Two-phase dispatch heuristic to schedule the movement of multi-attribute mobile sensors in a hybrid wireless sensor network[J].IEEE Transactions on Mobile Computing,2014,13(4):709-722.
[8]ZHANG Lin,YIN Na,WANG Ruchuan.Research on malicious node identification based on DPAM-MD algorithm in wireless sensor networks[J].Journal of Communications,2015,36(S1):1-7(in Chinese).[张琳,尹娜,王汝传.无线传感网中基于DPAM-MD算法的恶意节点识别研究[J].通信学报,2015,36(S1):1-7.]
[9]CAI Shaobin,HAN Qilong,GAO Zhenguo,et al.Research on cloud based sensor node identification technology in wireless sensor network[J].Acta Electronica Sinica,2012,40(11):2232-2238(in Chinese).[蔡绍滨,韩启龙,高振国,等.基于云模型的无线传感器网络恶意节点识别技术的研究[J].电子学报,2012,40(11):2232-2238.]
[10]TONG Weiming,LIANG Jianquan,LU Lei,et al.Intrusion detection scheme based node trust value in WSNs[J].Systems Engineering and Electronics,2015,37(7):1644-1649(in Chinese).[佟为明,梁建权,卢雷,等.基于节点信任值的WSNs入侵检测方案[J].系统工程与电子技术,2015,37(7):1644-1649.]
[11]Ho JW,Wright M,Das SK.Distributed detection of mobile malicious node attacks in wireless sensor networks[J].Ad Hoc Networks,2012,10(3):512-523.
[12]Ning YU,Wan J.Repeated game based localization algorithm for wireless sensor networks with malicious beacon nodes[J].Ad Hoc&Sensor Wireless Networks,2015,25(1):45-68.
[13]Cuadros-Rodríguez L,Pérez-Casta1o E, Ruiz-Samblás C.Quality performance metrics in multivariate classification methods for qualitative analysis[J].Trac Trends in Analytical Chemistry,2016,80(1):612-624.
[14]Kim H.Best linear classification rule for multivariate interval screened data[J].Communications in Statistics-Theory and Methods,2015,44(8):1669-1690.
[15]Zhou PY,Chan KCC.A feature extraction method for multivariate time series classification using temporal patterns[C]//PAKDD,2015:409-421.
[16]Dai H,Liu H,Jia Z.Dynamic malicious node detection with semi-supervised multivariate classification in cognitive wireless sensor networks[J].Concurrency&Computation Practice&Experience,2015,27(12):2910-2923.