面向物联网的入侵检测技术研究新进展

doi:10.3969/j.issn.1671-1122.2024.02.001

摘要/Abstract

摘要：

相较于传统入侵检测机制，智能化的入侵检测技术能够充分提取数据特征，具有更高的检测效率，但对数据样本标签的要求也更高。文章按数据样本标签从有监督和无监督角度对物联网入侵检测技术的最新进展进行综述。首先概述了基于签名的入侵检测方法，并基于有监督和无监督的分类分析了近期基于传统机器学习的入侵检测方法;然后分析了近期基于深度学习的入侵检测方法，分别对基于有监督、无监督、生成对抗网络和深度强化学习的入侵检测方法进行分析;最后分析总结了物联网入侵检测技术的研究挑战和未来的研究趋势。

关键词: 物联网, 入侵检测, 机器学习, 深度学习, 生成对抗网络

Abstract:

Compared to traditional intrusion detection mechanisms, the intelligent intrusion detection technology can fully extract data features, demonstrating higher detection efficiency, however, it also imposes greater demands on data sample labels. Considering data sample labels, this article provided a comprehensive review of the latest developments in the intrusion detection technology for the Internet of things(IoT) from the perspectives of supervised and unsupervised learning. Firstly, it outlined signature-based intrusion detection methods and analyzed recent traditional machine learning based intrusion detection methods based on the classification of supervised and unsupervised learning. Then, it analyzed recent deep learning based intrusion detection methods based on supervised, unsupervised, generative adversarial network, and deep reinforcement learning, respectively. Finally, it summarized the research challenges and future trends in the IoT intrusion detection technology.

Key words: Internet of things, intrusion detection, machine learning, deep learning, generative adversarial network

中图分类号:

TP309

冯光升, 蒋舜鹏, 胡先浪, 马明宇. 面向物联网的入侵检测技术研究新进展[J]. 信息网络安全, 2024, 24(2): 167-178.

FENG Guangsheng, JIANG Shunpeng, HU Xianlang, MA Mingyu. New Research Progress on Intrusion Detection Techniques for the Internet of Things[J]. Netinfo Security, 2024, 24(2): 167-178.

图/表 10

表1

图1

表2

表3

表4

图2

表5

表6

表7

表8

参考文献 64

[1]	HASAN K F, KAUR T, HASAN M M, et al. Cognitive Internet of Vehicles: Motivation, Layered Architecture and Security Issues[C]//IEEE. 2019 International Conference on Sustainable Technologies for Industry 4.0(STI). New York: IEEE, 2019: 1-6.
[2]	SISINNI E, SAIFULLAH A, HAN S, et al. Industrial Internet of Things: Challenges, Opportunities, and Directions[J]. IEEE Transactions on Industrial Informatics, 2018, 14(11): 4724-4734. doi: 10.1109/TII.2018.2852491 URL
[3]	ABDALJABAR Z H, UCAN O N, ALHEETI K M A. An Intrusion Detection System for IoT Using KNN and Decision-Tree Based Classification[C]// IEEE. 2021 International Conference of Modern Trends in Information and Communication Technology Industry(MTICTI). New York:IEEE, 2021: 1-5.
[4]	GUEZZAZ A, BENKIRANE S, AZROUR M, et al. A Reliable Network Intrusion Detection Approach Using Decision Tree with Enhanced Data Quality[EB/OL]. (2021-01-01)[2023-10-12]. https://doi.org/10.1155/2021/1230593.
[5]	KASONGO S M. An Advanced Intrusion Detection System for IIoT Based on GA and Tree Based Algorithms[J]. IEEE Access, 2021, 9: 113199-113212. doi: 10.1109/ACCESS.2021.3104113 URL
[6]	SABA T, SADAD T, REHMAN A, et al. Intrusion Detection System through Advance Machine Learning for the Internet of Things Networks[J]. IT Professional, 2021, 23(2): 58-64.
[7]	KESERWANI P K, GOVIL M C, PILLI E S, et al. A Smart Anomaly-Based Intrusion Detection System for the Internet of Things(IoT) Network Using GWO-PSO-RF Model[J]. Journal of Reliable Intelligent Environments, 2021, 7: 3-21. doi: 10.1007/s40860-020-00126-x
[8]	ZHOU Jieying, HE Pengfei, QIU Rongfa, et al. Research on Intrusion Detection Based on Random Forest and Gradient Boosting Tree[J]. Journal of Software, 2021, 32(10): 3254-3265.
	周杰英, 贺鹏飞, 邱荣发, 等. 融合随机森林和梯度提升树的入侵检测研究[J]. 软件学报, 2021, 32(10):3254-3265.
[9]	GU Jie, LU Shan. An Effective Intrusion Detection Approach Using SVM with Naïve Bayes Feature Embedding[EB/OL]. (2021-04-01)[2023-10-12]. https://doi.org/10.1016/j.cose.2020.102158.
[10]	AHMAD M, RIAZ Q, ZEESHAN M, et al. Intrusion Detection in Internet of Things Using Supervised Machine Learning Based on Application and Transport Layer Features Using UNSW-NB15 Data-Set[J]. EURASIP Journal on Wireless Communications and Networking, 2021(1): 1-23.
[11]	SARHAN M, LAYEGHY S, MOUSTAFA N, et al. Feature Extraction for Machine Learning-Based Intrusion Detection in IoT networks[EB/OL]. (2022-09-07)[2023-10-12]. https://www.sciencedirect.com/science/article/pii/S2352864822001754.
[12]	MANHAS J, KOTWAL S. Implementation of Intrusion Detection System for Internet of Things Using Machine Learning Techniques[EB/OL]. (2021-01-12)[2023-10-12]. https://doi.org/10.1007/978-981-15-8711-5_11.
[13]	VERMA A, RANGA V. Machine Learning Based Intrusion Detection Systems for IoT Applications[J]. Wireless Personal Communications, 2020, 111: 2287-2310. doi: 10.1007/s11277-019-06986-8
[14]	HAZMAN C, GUEZZAZ A, BENKIRANE S, et al. lIDS-SIoEL: Intrusion Detection Framework for IoT-Based Smart Environments Security Using Ensemble Learning[J]. Cluster Computing, 2023, 26(6): 4069-4083. doi: 10.1007/s10586-022-03810-0
[15]	ABBAS A, KHAN M A, LATIF S, et al. A New Ensemble-Based Intrusion Detection System for Internet of Things[J]. Arabian Journal for Science and Engineering, 2022, 47: 1805-1819. doi: 10.1007/s13369-021-06086-5
[16]	OKEY O D, MAIDIN S S, ADASME P, et al. BoostedEnML: Efficient Technique for Detecting Cyberattacks in IoT Systems Using Boosted Ensemble Machine Learning[EB/OL]. (2022-09-19)[2023-10-12]. https://doi.org/10.3390/s22197409.
[17]	HAN Weixiang, PENG Jialiang, YU Jiahua, et al. Heterogeneous Data-Aware Federated Learning for Intrusion Detection Systems via Meta-Sampling in Artificial Intelligence of Things[EB/OL]. (2020-11-12)[2023-10-12]. https://doi.org/10.48550/arXiv.2011.06393.
[18]	SHAN Yao, YAO Yu, ZHOU Xiaoming, et al. CFL-IDS: An Effective Clustered Federated Learning Framework for Industrial Internet of Things Intrusion Detection[EB/OL]. (2023-10-13)[2023-11-12]. https://ieeexplore.ieee.org/document/10285326.
[19]	WEN Weiping, HU Yezhou, ZHAO Guoliang, et al. Design and Implementation of an Abnormal IP Identification System Based on Traffic Feature Classification[J]. Netinfo Security, 2021, 21(8): 1-9.
	文伟平, 胡叶舟, 赵国梁, 等. 基于流量特征分类的异常IP识别系统的设计与实现[J]. 信息网络安全, 2021, 21(8):1-9.
[20]	MOHY-EDDINE M, GUEZZAZ A, BENKIRANE S, et al. An Efficient Network Intrusion Detection Model for IoT Security Using K-NN Classifier and Feature Selection[J]. Multimedia Tools and Applications, 2023, 82: 23615-23633. doi: 10.1007/s11042-023-14795-2
[21]	ABDELMOUMIN G, RAWAT D B, RAHMAN A. On the Performance of Machine Learning Models for Anomaly-Based Intelligent Intrusion Detection Systems for the Internet of Things[J]. IEEE Internet of Things Journal, 2021, 9(6): 4280-4290. doi: 10.1109/JIOT.2021.3103829 URL
[22]	WAHAB O A. Intrusion Detection in the IoT under Data and Concept Drifts: Online Deep Learning Approach[J]. IEEE Internet of Things Journal, 2022, 9(20): 19706-19716. doi: 10.1109/JIOT.2022.3167005 URL
[23]	NASIR M, JAVED A R, TARIQ M A, et al. Feature Engineering and Deep Learning-Based Intrusion Detection Framework for Securing Edge IoT[J]. The Journal of Supercomputing, 2022, 78: 8852-8866. doi: 10.1007/s11227-021-04250-0
[24]	ASHFAQ R A R, WANG Xizhao, HUANG J Z, et al. Fuzziness Based Semi-Supervised Learning Approach for Intrusion Detection System[J]. Information Sciences, 2017, 378: 484-497. doi: 10.1016/j.ins.2016.04.019 URL
[25]	LI Wenjuan, MENG Weizhi, AU M H. Enhancing Collaborative Intrusion Detection via Disagreement-Based Semi-Supervised Learning in IoT Environments[J]. Journal of Network and Computer Applications, 2020, 161: 1-12.
[26]	ZHAO Ruijie, WANG Yijun, XUE Zhi, et al. Semi-Supervised Federated Learning Based Intrusion Detection Method for Internet of Things[J]. IEEE Internet of Things Journal, 2022, 10: 8645-8657. doi: 10.1109/JIOT.2022.3175918 URL
[27]	VADIGI S, SETHI K, MOHANTY D, et al. Federated Reinforcement Learning Based Intrusion Detection System Using Dynamic Attention Mechanism[J]. Journal of Information Security and Applications, 2023, 78: 1-15.
[28]	RAMANA T, THIRUNAVUKKARASAN M, MOHAMMED A S, et al. Ambient Intelligence Approach: Internet of Things Based Decision Performance Analysis for Intrusion Detection[J]. Computer Communications, 2022, 195: 315-322. doi: 10.1016/j.comcom.2022.09.007 URL
[29]	CHEN Yi, LIN Qiuzhen, WEI Wenhong, et al. Intrusion Detection Using Multi-Objective Evolutionary Convolutional Neural Network for Internet of Things in Fog Computing[J]. Knowledge-Based Systems, 2022, 244: 1-14.
[30]	ALJUMAH A. IoT-Based Intrusion Detection System Using Convolution Neural Networks[J]. PeerJ Computer Science, 2021, 7: 1-19.
[31]	KAN Xiu, FAN Yixuan, FANG Zhijun, et al. A Novel IoT Network Intrusion Detection Approach Based on Adaptive Particle Swarm Optimization Convolutional Neural Network[J]. Information Sciences, 2021, 568: 147-162. doi: 10.1016/j.ins.2021.03.060 URL
[32]	ROOPAK M, TIAN G Y, CHAMBERS J. An Intrusion Detection System Against DDoS Attacks in IoT Networks[C]// IEEE. 2020 10th Annual Computing and Communication Workshop and Conference(CCWC). New York:IEEE, 2020: 562-567.
[33]	ALMIANI M, ABUGHAZLEH A, AL-RAHAYFEH A, et al. Deep Recurrent Neural Network for IoT Intrusion Detection System[J]. Simulation Modelling Practice and Theory, 2020, 101: 1-20.
[34]	SARAVANAN V, MADIAJAGAN M, RAFEE S M, et al. IoT-Based Blockchain Intrusion Detection Using Optimized Recurrent Neural Network[EB/OL]. (2023-09-16)[2023-10-12]. https://link.springer.com/article/10.1007/s11042-023-16662-6.
[35]	SAHEED Y K, AROWOLO M O. Efficient Cyber Attack Detection on the Internet of Medical Things-Smart Environment Based on Deep Recurrent Neural Network and Machine Learning Algorithms[J]. IEEE Access, 2021, 9: 161546-161554. doi: 10.1109/ACCESS.2021.3128837 URL
[36]	ALIMI A, OUAHADA K, ABU-MAHFOUZ A M, et al. Refined LSTM Based Intrusion Detection for Denial-of-Service Attack in Internet of Things[J]. Journal of Sensor and Actuator Networks, 2022, 11(3): 1-14. doi: 10.3390/jsan11010001 URL
[37]	HANAFI A V, GHAFFARI A, REZAEI H, et al. Intrusion Detection in Internet of Things Using Improved Binary Golden Jackal Optimization Algorithm and LSTM[EB/OL]. (2023-08-25)[2023-10-12]. https://link.springer.com/article/10.1007/s10586-023-04102-x.
[38]	DEORE B, BHOSALE S. Hybrid Optimization Enabled Robust CNN-LSTM Technique for Network Intrusion Detection[J]. IEEE Access, 2022, 10: 65611-65622. doi: 10.1109/ACCESS.2022.3183213 URL
[39]	YAIR Meidan. Detection_of_IoT_Botnet_Attacks_N_BaIoT.[EB/OL]. (2018-03-18)[2023-10-12]. http://archive.ics.uci.edu/dataset/442/detection+of+iot+botnet+attacks+n+baiot.
[40]	IMRANA Y, XIANG Y, ALI L, et al. A Bidirectional LSTM Deep Learning Approach for Intrusion Detection[EB/OL]. (2021-12-15)[2023-10-12]. https://doi.org/10.1016/j.eswa.2021.115524.
[41]	ABOELWAFA M M, SEDDIK K G, ELDEFRAWY M H, et al. A Machine-Learning-Based Technique for False Data Injection Attacks Detection in Industrial IoT[J]. IEEE Internet of Things Journal, 2020, 7(9): 8462-8471. doi: 10.1109/JIoT.6488907 URL
[42]	LUNARDI W T, LOPEZ M A, GIACALONE J P. Arcade: Adversarially Regularized Convolutional Autoencoder for Network Anomaly Detection[J]. IEEE Transactions on Network and Service Management, 2022, 20(2): 1305-1318. doi: 10.1109/TNSM.2022.3229706 URL
[43]	WANG Wenjuan, DU Xuehui, SHAN Dibin, et al. Cloud Intrusion Detection Method Based on Stacked Contractive Auto-Encoder and Support Vector Machine[J]. IEEE Transactions on Cloud Computing, 2020, 10(3): 1634-1646. doi: 10.1109/TCC.2020.3001017 URL
[44]	LU Huimin, WANG Tian, XU Xing, et al. Cognitive Memory-Guided Autoencoder for Effective Intrusion Detection in Internet of Things[J]. IEEE Transactions on Industrial Informatics, 2021, 18(5): 3358-3366. doi: 10.1109/TII.2021.3102637 URL
[45]	ALMOGREN A S. Intrusion Detection in Edge-of-Things Computing[J]. Journal of Parallel and Distributed Computing, 2020, 137: 259-265. doi: 10.1016/j.jpdc.2019.12.008 URL
[46]	LU Kangdi, ZENG Guoqing, LUO Xiaozhao, et al. Evolutionary Deep Belief Network for Cyber-Attack Detection in Industrial Automation and Control System[J]. IEEE Transactions on Industrial Informatics, 2021, 17(11): 7618-7627. doi: 10.1109/TII.2021.3053304 URL
[47]	ELMASRY W, AKBULUT A, ZAIM A H. Evolving Deep Learning Architectures for Network Intrusion Detection Using a Double PSO Metaheuristic[EB/OL]. (2020-02-26)[2023-10-14]. https://doi.org/10.1016/j.comnet.2019.107042.
[48]	CHEN Aiguo, FU Yang, ZHENG Xu, et al. An Efficient Network Behavior Anomaly Detection Using a Hybrid DBN-LSTM Network[EB/OL]. (2022-03-15)[2023-10-12]. https://doi.org/10.1016/j.cose.2021.102600.
[49]	MUHAMMAD G, HOSSAIN M S, GARG S. Stacked Autoencoder-Based Intrusion Detection System to Combat Financial Fraudulent[J]. IEEE Internet of Things Journal, 2023, 10(3): 2071-2078. doi: 10.1109/JIOT.2020.3041184 URL
[50]	SINGH P, KAUR A, AUJLA G S, et al. Daas: Dew Computing as a Service for Intelligent Intrusion Detection in Edge-of-Things Ecosystem[J]. IEEE Internet of Things Journal, 2021, 8(16): 12569-12646. doi: 10.1109/JIOT.2020.3029248 URL
[51]	SCHLEGL T, SEEBÖCK P, WALDSTEIN S M, et al. Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery[C]// Springer. The 25th International Conference on Information Processing in Medical Imaging. Heidelberg: Springer, 2017: 146-157.
[52]	ZENATI H, FOO C S, LECOUAT B, et al. Efficient Gan-Based Anomaly Detection[EB/OL]. (2019-05-01)[2023-10-22]. https://arxiv.org/pdf/1802.06222.pdf.
[53]	SEO E, SONG H M, KIM H K. GIDS: GAN Based Intrusion Detection System for In-Vehicle Network[C]// IEEE. 2018 16th Annual Conference on Privacy, Security and Trust(PST). New York:IEEE, 2018: 1-6.
[54]	CHEN Hongyu, JIANG Li. Efficient GAN-Based Method for Cyber-Intrusion Detection[EB/OL]. (2019-07-24)[2023-10-22]. https://arxiv.org/abs/1904.02426.
[55]	LIU Yongmin, YANG Yujin, LUO Haoyi, et al. Intrusion Detection Method for Wireless Sensor Network Based on Bidirectional Circulation Generative Adversarial Network[J]. Journal of Computer Applications, 2023, 43(1): 160-168. doi: 10.11772/j.issn.1001-9081.2021112001
	刘拥民, 杨钰津, 罗皓懿, 等. 基于双向循环生成对抗网络的无线传感网入侵检测方法[J]. 计算机应用, 2023, 43(1):160-168. doi: 10.11772/j.issn.1001-9081.2021112001
[56]	ZHANG Huiyan, LIANG Yong, LAN Jinghong, et al. Intrusion Detection Method Based on a Memory Module and a Filtered Generative Adversarial Network[EB/OL]. (2023-11-15)[2023-11-20]. https://doi.org/10.19678/j.issn.1000-3428.0068157.
	张慧妍, 梁勇, 兰景宏, 等. 基于记忆模块和过滤式生成对抗网络的入侵检测方法[EB/OL]. (2023-11-15)[2023-11-20]. https://doi.org/10.19678/j.issn.1000-3428.0068157.
[57]	DING Hongwei, SUN Yu, HUANG Nana, et al. TMG-GAN: Generative Adversarial Networks-Based Imbalanced Learning for Network Intrusion Detection[J]. IEEE Transactions on Information Forensics and Security, 2023, 19: 1156-1167. doi: 10.1109/TIFS.2023.3331240 URL
[58]	HSU Y F, MATSUOKA M. A Deep Reinforcement Learning Approach for Anomaly Network Intrusion Detection System[C]// IEEE. 2020 IEEE 9th International Conference on Cloud Networking(CloudNet). New York:IEEE, 2020: 1-6.
[59]	PRIYA S, KUMAR K. Feature Selection with Deep Reinforcement Learning for Intrusion Detection System[J]. Computer Systems Science & Engineering, 2023, 46(3): 3339-3353.
[60]	ALAVIZADEH H, ALAVIZADEH H, JANG-JACCARD J. Deep Q-Learning Based Reinforcement Learning Approach for Network Intrusion Detection[J]. Computers, 2022, 11(3): 41-59. doi: 10.3390/computers11030041 URL
[61]	LI Beibei, SONG Jiarui, DU Qingyun, et al. DRL-IDS: Deep Reinforcement Learning-Based Intrusion Detection System for Industrial Internet of Things[J]. Computer Science, 2021, 48(7): 47-54. doi: 10.11896/jsjkx.210400021
	李贝贝, 宋佳芮, 杜卿芸, 等. DRL-IDS:基于深度强化学习的工业物联网入侵检测系统[J]. 计算机科学, 2021, 48(7):47-54. doi: 10.11896/jsjkx.210400021
[62]	LI Ziruo, SHEN Xi, ZHANG Yibing, et al. Network Anomaly Detection Method for Smart Substation Based on Deep Reinforcement Learning[J]. Southern Power System Technology, 2021, 15(6): 98-105.
	李自若, 沈曦, 张亦兵, 等. 基于深度强化学习的智慧变电站网络异常检测方法[J]. 南方电网技术, 2021, 15(6):98-105.
[63]	WANG Zhihao, JIANG Dingde, LV Zhihan, et al. A Deep Reinforcement Learning Based Intrusion Detection Strategy for Smart Vehicular Networks[C]// IEEE. INFOCOM 2022-IEEE Conference on Computer Communications Workshops(INFOCOM WKSHPS). New York:IEEE, 2022: 1-6.
[64]	RIZZARDI A, SICARI S, PORISINI A C. Deep Reinforcement Learning for Intrusion Detection in Internet of Things: Best Practices, Lessons Learnt, and Open Challenges[EB/OL]. (2023-10-10)[2023-11-12]. https://doi.org/10.1016/j.comnet.2023.110016.

方法	特点描述	优点	缺点
签名增强	将网络上下文信息添加到签名中，提高灵活性	降低虚警率，提高分析流量的准确性	签名复杂，修改繁琐
状态签名	通过记住先前包的状态信息，跨多个包进行攻击分析	可检测多阶段攻击，灵活适应不同攻击场景	处理开销增加
漏洞签名	使用漏洞语境检测复杂攻击	使用应用程序语义，减少虚警数量	计算开销较大，尚无真实实例
报警验证	主动或被动验证IDS生成的报警，确定攻击是否成功，并验证对目标网络的影响	几乎实时验证报警，降低虚警率	可能受到欺骗技术的影响，依赖于服务器响应

方案	数据集	机器学习方法	评价指标
MANHAS^[12]等人	KDD99	KNN、SVM、DT、朴素贝叶斯	准确率、灵敏度、精确度、F1分数
VERMA^[13]等人	CIDDS-001、UNSWNB15、NSL-KDD	随机森林、AdaBoost	准确率、灵敏度、AUC、检测率
ABBAS^[15]等人	CICIDS2017	集成学习	准确率
ABDALJABAR^[3]等人	DoH20	KNN	准确率、检测率
GUEZZAZ^[4]等人	NSL-KDD、CICIDS2017	DT	准确率、检测率、误报率
KASONGO^[5]等人	UNSWNB15	GA-RF	准确率、AUC
KESERWANI^[7]等人	KDDCup99、NSL-KDD、CICIDS-2017	GWO-PSO-RF	准确率
GU^[9]等人	UNSWNB15、CICIDS2017、NSL-KDD、Kyoto 2006+	NB-SVM	准确率、检测率、虚警率
HAZMAN^[14]等人	BoT-IoT、IoT-23	集成学习	准确率、精确度、F1分数、误报率
AHMAD^[10]等人	UNSWNB15	RF、SVM、ANN	准确率
OKEY^[16]等人	CICIDS2017、CSE-CIC-IDS2018	BoostedEnML	准确率、精确度、AUC、F1分数
周杰英^[8]等人	UNSW-NB15	RF-GBDT	检测率、虚警率、F1分数、AUC

模型	面向问题	特点	数据集
半朴素贝叶斯IDS	—	在半监督场景保持低假阳性的同时提高入侵检测精确度	KDDCup1999
主动多视图协同训练IDS	—	多视图、主动学习	KDDCup1999
非参数的半监督学习	半监督入侵检测模型实际部署不理想	摆脱数据集的非现实约束	Kyoto2006+
基于模糊算法的IDS	提高数据的可扩展性	神经网络作为分类器	SL-KDD
基于分歧的半监督IDS	模型违反假设、损失函数的非凸性、学习算法可扩展性差等问题	能够在真实物联网环境上进行部署	KDDCup1999、自建数据集

方案	特点	评价指标
MOHY-EDDINE^[20]等人	采用PCA、单变量统计检验和遗传算法进行特征选择，以提高数据质量并选出k个表现最好的特征	准确率、检测率、虚警率、预测时间和误报率
NASIR^[23]等人	采用SpiderMonkey（SM）、PCA、信息增益和相关属性评价进行特征选择	准确率、F1分数、AUC-ROC值
WAHAB^[22]等人	利用PCA法分析数据流中特征方差的变化	准确率
VADIGI^[27]等人	所有智能体可通过注意力加权模型聚合过程从其他智能体可用数据的分布和模式中获益	准确率、精确度、假阳性率和AUC
RAMANA^[28]等人	基于深度Q网络的深度神经网络集成强化学习，用于边缘云基础架构的入侵检测	准确率、精确度和召回率

方案	特点	数据集	评价指标
CHEN^[29]等人	多目标进化CNN，运行在物联网雾计算的雾节点上	AWID、CIC-IDS2107	精确度、准确率、召回率、F1分数
ALJUMAH^[30]等人	时间CNN，整合了CNN和通用卷积的物联网入侵检测智能模型，解决了数据集不平衡问题	Bot-IoT	精确度、准确率、召回率、F1分数、日志损失
KAN^[31]等人	自适应粒子群优化CNN，用于物联网入侵检测	开源数据集^[39]	精确度、准确率、召回率、F1分数
ROOPAK^[32]等人	融合跳跃基因适应NSGA-II多目标优化方法和集成LSTM的CNN，用于数据降维和深度学习	CICIDS2017	精确度、准确率、召回率、F1分数
ALMIANI^[33]等人	基于深度RNN的物联网IDS	NSL-KDD	准确率、精确度、Mathew相关性、Cohen的Kappa系数
SARAVANAN^[34]等人	结合区块链的BbAB方案和优化的RNN	MED	准确率、精确度、召回率、F1分数、检测率
SAHEED^[35]等人	基于DRNN和监督机器学习模型的IDS	CICIDS	精确度、召回率、F1分数
ALIMI^[36]等人	RLSTM模型	CICIDS-2017、NSL-KDS	精确度、召回率、F1分数
IMRANA^[40]等人	BiDLSTM模型	NSL-KDD	精确度、准确率、召回率、F1分数
HANAFI^[37]等人	基于改进的二进制Golden Jackal优化算法和LSTM网络的IDS	NSL-KDD、CICIDS2017	精确度、准确率、召回率、F1分数
DEORE^[38]等人	基于黑猩猩鸡群优化的深度LSTM，强调CNN的特征提取和LSTM的检测性能	NSL-KDD、BoT-IoT	准确率、敏感度