High-Reliability Intrusion Detection Algorithm Under Conformal Prediction Framework

doi:10.19678/j.issn.1000-3428.0063144

Abstract

Abstract: Intrusion detection algorithms are widely used in the field of network security.However, existing intrusion detection algorithms based on machine learning only output prediction result labels for data and lack evaluation mechanisms for the confidence value of prediction results, making it difficult to ensure the reliability of results.This study proposes a high-reliability intrusion detection algorithm based on Conformal Prediction(CP).CP is integrated into a traditional machine learning algorithm to obtain data classification labels and corresponding confidence values to improve the reliability of network data classification.By digitalization, standardization and reducing the dimensionality of network data according to the characteristics of traditional machine learning algorithms, an inconsistent score calculation formula under the CP framework is designed and a smoothing factor is introduced to improve the calculation of p-value.The improved p-value calculation formula can calculate the p-value of prediction results smoothly and improve the overall stability of the algorithm.Experimental results demonstrate that compared to the SVM, DT and DT-SVM algorithms alone, the classification accuracy of the proposed algorithm on the KDD CUP99 dataset is improved by 11.1, 4.6, and 3.7 percentage points, respectively, and that on the AWID dataset is improved by 4.0, 2.5, and 1.3 percentage points, respectively, which ensures the high-reliability of intrusion detection results.

Key words: Conformal Prediction(CP), intrusion detection, high-reliability, machine learning, confidence value, inconsistent measure

摘要： 入侵检测算法广泛应用于网络安全领域，然而现有基于机器学习的入侵检测算法仅输出数据的预测结果标签，缺少对预测结果置信值的评价机制，难以确保预测结果的可靠性。提出一种基于共形预测的高可靠入侵检测算法。将共形预测融入到传统机器学习算法中，得到数据分类标签和对应的置信值、可信度，提高网络数据分类的可靠性。通过对网络数据进行数字化、标准化和降维预处理，根据传统机器学习算法的特点，设计在共形预测框架下与各算法相对应的不一致得分计算公式，并引入平滑因子改进p-value的计算公式，使其能够以更平滑的方式计算预测结果p-value，提高算法的稳定性。实验结果表明，与单独采用SVM、DT和DT-SVM算法相比，该算法在KDD CUP99数据集上分类准确率分别提高11.1、4.6和3.7个百分点，在AWID数据集上分类准确率分别提高4.0、2.5和1.3个百分点，可保证入侵检测结果的高可靠性。

关键词: 共形预测, 入侵检测, 高可靠性, 机器学习, 置信值, 不一致测量

CLC Number:

TP309

JIN Haibo, ZHAO Xinyue. High-Reliability Intrusion Detection Algorithm Under Conformal Prediction Framework[J]. Computer Engineering, 2022, 48(7): 130-140.

金海波, 赵欣越. 共形预测框架下的高可靠入侵检测算法[J]. 计算机工程, 2022, 48(7): 130-140.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0063144

http://www.ecice06.com/EN/Y2022/V48/I7/130

Figures/Tables 16

References

[1] LIAO H J, LIN C H R, LIN Y C, et al.Intrusion detection system:a comprehensive review[J].Journal of Network and Computer Applications, 2013, 36(1):16-24.
[2] CHEN W Z, LIU T J, TANG Y, et al.Multi-level adaptive coupled method for industrial control networks safety based on machine learning[J].Safety Science, 2019, 120:268-275.
[3] THASEEN I S, KUMAR C A.Intrusion detection model using fusion of Chi-square feature selection and multi class SVM[J].Journal of King Saud University-Computer and Information Sciences, 2017, 29(4):462-472.
[4] AL-YASEEN W L, OTHMAN Z A, NAZRI M Z A.Multi-level hybrid support vector machine and extreme learning machine based on modified K-means for intrusion detection system[J].Expert Systems with Applications, 2017, 67:296-303.
[5] LI X K, CHEN W, ZHANG Q R, et al.Building auto-encoder intrusion detection system based on random forest feature selection[J].Computers & Security, 2020, 95:1-10.
[6] JIANG F, SUI Y F, CAO C G.An incremental decision tree algorithm based on rough sets and its application in intrusion detection[J].Artificial Intelligence Review, 2013, 40(4):517-530.
[7] RESENDE P A A, DRUMMOND A C.A survey of random forest based methods for intrusion detection systems[J].ACM Computing Surveys, 2019, 51(3):1-36.
[8] GUAN Z Y, YANG S Q, SUN H, et al.Fine-grained knowledge sharing in collaborative environments[J].IEEE Transactions on Knowledge and Data Engineering, 2015, 27(8):2163-2174.
[9] ZHOU Y Y, CHENG G, JIANG S Q, et al.Building an efficient intrusion detection system based on feature selection and ensemble classifier[J].Computer Networks, 2020, 174:1-10.
[10] SAFAEI M, ISMAIL A S, CHIZARI H, et al.Standalone noise and anomaly detection in wireless sensor networks:a novel time-series and adaptive Bayesian-network-based approach[J].Software:Practice and Experience, 2020, 50(4):428-446.
[11] 王振东, 徐振宇, 李大海, 等.面向入侵检测的元图神经网络构建与分析[J/OL].自动化学报:1-24[2021-10-01]. https://doi.org/10.16383/j.aas.c200819. WANG Z D, XU Z Y, LI D H, et al.Construction and analysis of meta-graph neural Network for intrusion Detection[J/OL].Acta Automatica Sinica:1-24[2021-10-01].https://doi.org/10.16383/j.aas.c200819.(in Chinese)
[12] ASHFAQ R A R, WANG X Z, HUANG J Z, et al.Fuzziness based semi-supervised learning approach for intrusion detection system[J].Information Sciences, 2017, 378:484-497.
[13] VINAYAKUMAR R, SOMAN K P, POORNACHANDRAN P.Applying convolutional neural network for network intrusion detection[C]//Proceedings of International Conference on Advances in Computing, Communications and Informatics.Washington D.C., USA:IEEE Press, 2017:1222-1228.
[14] LIAO Y H, VEMURI V R.Use of K-nearest neighbor classifier for intrusion detection[J].Computers & Security, 2002, 21(5):439-448.
[15] 任家东, 刘新倩, 王倩, 等.基于KNN离群点检测和随机森林的多层入侵检测方法[J].计算机研究与发展, 2019, 56(3):566-575. REN J D, LIU X Q, WANG Q, et al.An multi-level intrusion detection method based on KNN outlier detection and random forests[J].Journal of Computer Research and Development, 2019, 56(3):566-575.(in Chinese)
[16] ZHANG Y C, WANG L F, SUN W Q, et al.Distributed intrusion detection system in a multi-layer network architecture of smart grids[J].IEEE Transactions on Smart Grid, 2011, 2(4):796-808.
[17] FANG W J, TAN X L, WILBUR D.Application of intrusion detection technology in network safety based on machine learning[J].Safety Science, 2020, 124:1-10.
[18] VOVK V, GAMMERMANA, SHAFER G.Algorithmic learning in a random world[EB/OL].[2021-10-01].https://link.springer.com/content/pdf/bfm%3A978-0-387-25061-8%2F1.pdf.
[19] MATIZ S, BARNER K E.Conformal prediction based active learning by linear regression optimization[J].Neurocomputing, 2020, 388:157-169.
[20] JOHANSSON U, LINUSSON H, LÖFSTRÖM T, et al.Interpretable regression trees using conformal prediction[J].Expert Systems with Applications, 2018, 97:394-404.
[21] MATIZ S, BARNER K E.Inductive conformal predictor for convolutional neural networks:applications to active learning for image classification[J].Pattern Recognition, 2019, 90:172-182.
[22] HIMABINDU T V R, PADMANABHAN V, PUJARI A K.Conformal matrix factorization based recommender system[J].Information Sciences, 2018, 467:685-707.
[23] ZHANG M, WANG Y, ZHANG W, et al.Inductive conformal prediction for silent speech recognition[J].Journal of Neural Engineering, 2020, 17(6):1-10.
[24] WANG D, WANG P, WANG C, et al.A conformal prediction inspired approach for distribution regression with random Fourier features[J].Applied Soft Computing, 2020, 97:1-10.
[25] GRAJSKI K A, BREIMAN L, VIANA DI PRISCO G, et al.Classification of EEG spatial patterns with a tree-structured methodology:cart[J].IEEE Transactions on Bio-Medical Engineering, 1986, 33(12):1076-1086.

Please choose a citation manager

Content to export