摘要: 針對傳統(tǒng)機(jī)器學(xué)習(xí)方法對特征依賴大,,以及傳統(tǒng)卷積神經(jīng)網(wǎng)絡(luò)只通過提取重要的局部特征來完成識(shí)別分類,收斂速度慢的問題,,提出了一維多尺度卷積神經(jīng)網(wǎng)絡(luò)和門控循環(huán)單元相結(jié)合的入侵檢測方法,。該方法使用一維多尺度卷積神經(jīng)網(wǎng)絡(luò)加強(qiáng)對特征的捕捉能力,加快收斂速度,,采用門控循環(huán)單元把握空間特征,,減少通道數(shù)量擴(kuò)張,降低數(shù)據(jù)維度,。使用KDD CUP 99數(shù)據(jù)集和密西西比州大學(xué)的天然氣管道的數(shù)據(jù)集進(jìn)行仿真實(shí)驗(yàn),,結(jié)果表明與經(jīng)典的機(jī)器學(xué)習(xí)分類器相比,該方法具有較高的入侵檢測性能和較好的泛化能力,。
中圖分類號(hào): TP391.9 文獻(xiàn)標(biāo)識(shí)碼: A DOI: 10.19358/j.issn.2096-5133.2021.09.005 引用格式: 宗學(xué)軍,,宋治文,何戡,,等. 基于1d-MSCNN+GRU的工業(yè)入侵檢測方法研究[J].信息技術(shù)與網(wǎng)絡(luò)安全,,2021,40(9):25-31.
Research on industrial intrusion detection method based on 1d-MSCNN+GRU model
Zong Xuejun,,Song Zhiwen,,He Kan,Lian Lian
(College of Information Engineering,,Shenyang University of Chemical Technology,,Shenyang 110142,China)
Abstract: In order to solve the problem that traditional machine learning methods rely heavily on features, and traditional convolutional neural network only extracts important local features to complete recognition and classification, and the convergence speed is slow, an intrusion detection method combining 1-dimensional multiscale convolutional neural network and gated recurrent unit is proposed. In this method, 1-dimensional multiscale convolutional neural network is used to enhance the ability to capture features, speed up the convergence speed, and the gating cycle unit is used to grasp the spatial features, reduce the expansion of the number of channels and reduce the data dimension. The KDD CUP 99 data set and the natural gas pipeline data set of the University of Mississippi are used for simulation experiments. The results show that the method has higher intrusion detection performance and better generalization ability than the classical machine learning classifier.
隨著工業(yè)控制網(wǎng)絡(luò)(ICN)的高速發(fā)展,ICN安全已經(jīng)是全球性重要問題之一,,工業(yè)入侵檢測作為一種 ICN安全防護(hù)技術(shù)已成為研究熱點(diǎn),。在全球每年的網(wǎng)絡(luò)安全事故中,其中有上百起攻擊都是針對工業(yè)控制系統(tǒng)(Industrial Control System,,ICS),,雖然所占的比重只是網(wǎng)絡(luò)安全事件的一小部分,但是所造成的影響對國家而言都是巨大的,,最為嚴(yán)重的就是經(jīng)濟(jì)損失[1],。因此如何有效地從入侵?jǐn)?shù)據(jù)中選擇特征進(jìn)行多分類,并提高數(shù)據(jù)特征提取的準(zhǔn)確度,,在整個(gè)網(wǎng)絡(luò)信息安全領(lǐng)域具有重要的研究價(jià)值,。