Internet of things intrusion path detection method based on improved HMM

He Yangjun

doi:10.11959/j.issn.2096-109x.AQ26047

您当前的位置：

首页 >

文章列表页 >

Internet of things intrusion path detection method based on improved HMM

Papers | 更新时间：2026-07-15

- Internet of things intrusion path detection method based on improved HMM
- Chinese Journal of Network and Information Security Vol. 12, Issue 3, Pages: 167-178(2026)
- 作者机构：
  
  浙江省公众信息产业有限公司，浙江杭州310012
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.AQ26047
  CLC： TP115
- Received：27 February 2026，
  
  Revised：2026-05-16，
  
  Published：25 June 2026
- 稿件说明：
移动端阅览
何洋军. 基于改进HMM的物联网入侵路径检测方法[J]. 网络与信息安全学报, 2026, 12(3): 167-178.

He Yangjun. Internet of things intrusion path detection method based on improved HMM[J]. Chinese Journal of Network and Information Security, 2026, 12(3): 167-178.
何洋军. 基于改进HMM的物联网入侵路径检测方法[J]. 网络与信息安全学报, 2026, 12(3): 167-178. DOI： 10.11959/j.issn.2096-109x.AQ26047.

He Yangjun. Internet of things intrusion path detection method based on improved HMM[J]. Chinese Journal of Network and Information Security, 2026, 12(3): 167-178. DOI： 10.11959/j.issn.2096-109x.AQ26047.

摘要

针对物联网多步入侵路径隐蔽性强、标注数据稀缺及加密流量占比高等难题，对基于改进隐马尔可夫模型（HMM）的入侵路径检测进行了研究。构建融合网络拓扑、配置与漏洞信息的四元组入侵图模型，利用逻辑斯蒂函数量化状态转移概率，形成动态概率矩阵。针对传统HMM的零概率缺陷，设计基于语义相似性的最大似然概率重分配策略。引入状态转移修正系数与自适应动态阈值，构建多步迭代推断框架，实现告警序列智能筛选与入侵意图鲁棒识别。实验结果表明，该方法在复杂攻击场景下路径检测准确率达94%以上，具备良好的鲁棒性与可扩展性。

Abstract

A study was conducted on intrusion path detection based on an improved hidden Markov model (HMM) to address the challenges of strong concealment of multi-step intrusion paths in the Internet of Things

scarce annotated data

and high proportion of encrypted traffic. A quadruple intrusion graph model was constructed that integrated network topology

configuration

and vulnerability information

state transition probability was quantified using logistic functions

a dynamic probability matrix was formed

and a maximum likelihood probability reallocation strategy was designed based on semantic similarity for zero probability defects in traditional HMM. Introducing state transition correction coefficients and adaptive dynamic thresholds

a multi-step iterative inference framework was constructed to achieve intelligent screening of alarm sequences and robust recognition of intrusion intentions. The experimental results show that the method has an accuracy of over 94% in path detection in complex attack scenarios

and has good robustness and scalability.

关键词

Keywords

references

伍均玺 , 林峰 , 高红云 . 基于改进深度学习的主动式通信网络入侵行为自适应识别算法 [J ] . 微型电脑应用 , 2024 , 40 ( 4 ): 9 - 12 .

Wu J X , Lin F , Gao H Y . An Adaptive recognition algorithm for intrusion behavior in active communication networks based on improved deep learning [J ] . Microcomputer Applications , 2024 , 40 ( 4 ): 9 - 12 .

刘强 , 张颖 , 周卫祥 , 等 . 自适应类增量学习的物联网入侵检测系统 [J ] . 计算机工程 , 2023 , 49 ( 2 ): 169 - 174 .

Liu Q , Zhang Y , Zhou W X , et al . Adaptive class incremental learning-based IoT intrusion detection system [J ] . Computer Enginee- ring , 2023 , 49 ( 2 ): 169 - 174 .

Mansahaj S P , Rudra P S , Navneet K P , et al . A federated learning framework for enhanced data security and cyber intrusion detection in distributed network of underwater drones [J ] . IEEE Access , 2025 , 13 : 12634 - 12646 .

Lu Q Y , Gao Q Z , Li J N , et al . Distributed cyber-physical intrusion detection using stacking learning for wide-area protection system [J ] . Computer Communications , 2024 , 215 ( 6 ): 9151 - 1023 ..

李志辉 , 王德军 , 孙贝尔 . 基于知识图谱与HMM的入侵路径分析方法 [J ] . 中南民族大学学报(自然科学版) , 2025 , 44 ( 2 ): 226 - 236 .

Li Z H , Wang D J , Sun B R . Intrusion path analysis method based on knowledge graph and HMM [J ] . Journal of South-Central Minzu University(Natural Science Edition) , 2025 , 44 ( 2 ): 226 - 236 .

Bouzaachane K , Guarmah E M E , Alnajim A M , et al . Addressing modern cybersecurity challenges: a hybrid machine learning and deep learning approach for network intrusion detection [J ] . Compu- ters , Materials Continua, 2025 , 84 ( 2 ): 2391 - 2410 .

杨定坤 , 尹徐珊 , 孙澄宇 , 等 . 隐马尔可夫模型下电力信息网络入侵检测方法研究 [J ] . 自动化仪表 , 2025 , 46 ( 5 ): 94 - 99 .

Yang D K , Yin X S , Sun C Y , et al . Research on intrusion detection method in power information network under hidden Markov model [J ] . Process Automation Instrumentation , 2025 , 46 ( 5 ): 94 - 99 .

于洪 , 朱正彬 , 魏帅 , 等 . 基于异构执行体同步控制的入侵检测模型研究 [J ] . 网络与信息安全学报 , 2025 , 11 ( 1 ): 54 - 65 .

Yu H , Zhu Z B , Wei S H , et al . Research on intrusion detection model based on synchronization of heterogenous executer [J ] . Chinese Journal of Network and Information Security , 2025 , 11 ( 1 ): 54 - 65 .

蒋玉长 , 蒋利兵 , 黄凯 . FL-IoV: 基于联邦学习的综合车联网入侵检测方法 [J ] . 网络与信息安全学报 , 2025 , 11 ( 4 ): 127 - 140 .

Jiang Y C , Jiang L B , Huang K . FL-IoV: comprehensive intrusion detection method for internet of vehicles based on federated learning [J ] . Chinese Journal of Network and Information Security , 2025 , 11 ( 4 ): 127 - 140 .

Nandhini U , Kumar S V . An enhanced whale optimizer based on feature selection technique with effective ensemble classifier for network intrusion detection system [J ] . Peer-to-Peer Networking and Applications , 2025 , 18 ( 2 ): 1 - 28 .

朱静雯 , 许静 , 陈亮 , 等 . 基于隐马尔可夫模型的SQL注入攻击行为检测 [J ] . 计算机应用与软件 , 2023 , 40 ( 2 ): 331 - 338, 344 .

Zhu J W , Xu J , Chen L , et al . SQL injection attack detection based on hidden Markov model [J ] . Computer Applications and Software , 2023 , 40 ( 2 ): 331 - 338, 344 .

Naeem H , Ullah F , Srivastava G . Classification of intrusion cybe- r-attacks in smart power grids using deep ensemble learning with metaheuristic‐based optimization [J ] . Expert Systems , 2025 , 42 ( 1 ): 2354 - 8531 .

Bozorg C A , Zarakovitis C C , Ting T O , et al . Novel modeling and optimization for joint cybersecurity-vs-QoS intrusion detection mechanisms in 5G networks [J ] . Computer Networks , 2023 , 237 ( 2 ): 1 - 11 .

熊文定 , 罗凯伦 , 李睿 . 基于异常的终端级入侵检测 [J ] . 计算机系统应用 , 2023 , 32 ( 2 ): 181 - 189 .

Xiong W D , Luo K L , Li R . Anomaly-based terminal-level intrusion detection [J ] . Computer Systems Applications , 2023 , 32 ( 2 ): 181 - 189 .

Zhao J X , Zheng W . Cybersecurity entity recognition method combined with feedforward neural network enhancement [C ] // Proceedings of the 3rd International Conference on Machine Learning, Cloud Computing and Intelligent Mining (MLCCIM2024) . Berlin : Springer , 2025 : 95 - 104 .

Wang W Y , Li Q , Mu H L . Exploring malware complexities: a behavior and characteristic analysis approach for robust and accurate cybersecurity [J ] . Cluster Computing , 2024 , 28 ( 2 ): 82 .

Zhukabayeva T , Ahmad Z , Adamova A , et al . Penetration testing and machine learning-driven cybersecurity framework for IoT and smart city wireless networks [J ] . IEEE Access , 2025 , 13 ( 9 ): 86144 - 86166 .

胡威 , 庞九凤 , 张亚昊 , 等 . 一种基于隐马尔可夫链与分类赋权的网络安全态势评估模型研究 [J ] . 网络安全技术与应用 , 2023 ( 9 ): 29 - 33 .

Hu W , Pang J F , Zhang Y H , et al . Research on a network security situation assessment model based on hidden Markov chain and classification weighting [J ] . Network Security Technology Application , 2023 ( 9 ): 29 - 33 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Post-quantum encryption technology based on BRLWE for internet of things

Data sharing scheme for 5G IoT based on blockchain

Intelligent mining of App’s potential data sharing behavior

Differential analysis of the CRAFT algorithm based on deep learning

Lightweight quantum-resistant distributed consensus scheme for blockchain

Related Author

Yitian GAO

Liquan CHEN

Tianyang TU

Yuan GAO

Qianye CHEN

Kang QIAO

Wei YOU

Lingwei WANG

Related Institution

No data

⁰