
浏览全部资源
扫码关注微信
中北大学 软件学院, 山西 太原 030051
刘诗涵(2000-), 女, 硕士生, 主要从事网络测试与网络安全方面的研究。
赵利辉(1979-), 男, 副教授, 博士, 主要从事网络测试与网络安全方向的研究。E⁃mail: leehwi@nuc.edu.cn。
收稿:2025-09-07,
网络首发:2026-06-13,
纸质出版:2026-08-31
移动端阅览
刘诗涵, 赵利辉, 刘泽晋, 等. 基于递归图和MobileViT⁃AESTF的网络入侵检测模型[J]. 中北大学学报(自然科学版), 2026, 47(4): 531-540.
Liu Shihan, Zhao Lihui, Liu Zejin, et al. Network intrusion detection model based on recurrence plot and MobileViT⁃AESTF[J]. Journal of North University of China(Natural Science Edition), 2026, 47(4): 531-540.
刘诗涵, 赵利辉, 刘泽晋, 等. 基于递归图和MobileViT⁃AESTF的网络入侵检测模型[J]. 中北大学学报(自然科学版), 2026, 47(4): 531-540. DOI: 10.62756/jnuc.issn.1673-3193.2025.09.0004.
Liu Shihan, Zhao Lihui, Liu Zejin, et al. Network intrusion detection model based on recurrence plot and MobileViT⁃AESTF[J]. Journal of North University of China(Natural Science Edition), 2026, 47(4): 531-540. DOI: 10.62756/jnuc.issn.1673-3193.2025.09.0004.
针对当前网络入侵检测中流量图像化导致的时序特征丢失以及轻量化模型在复杂攻击下识别精度不足的问题, 提出一种基于递归图(Recurrence Plot, RP)与自适应高效时空融合模块(Adaptive Efficient Spatiotemporal Fusion, AESTF)的轻量化入侵检测模型MobileViT-AESTF。该方法利用相空间重构技术, 通过递归图将一维流量时间序列映射为二维状态空间中的递归关系, 有效保留了流量的非线性时序特征。针对MobileViT_V3在图像化流量处理中特征捕获能力不足的问题, 设计了AESTF模块。该模块包含高效时空融合单元(Efficient Spatiotemporal Fusion, ESTF)和自适应特征激励器(Adaptive Feature Exciter, AFE), 其中ESTF通过双路径异构注意力机制并行提取空间与通道特征, AFE则基于神经元能量函数自适应增强关键判别特征。在CIC UNSW-NB15 Augmented数据集上的实验结果表明, MobileViT-AESTF在保持较低参数量(1.04×10
6
)的同时, 检测准确率、 召回率及
F
1分数分别达到了99.84%、 99.82%和99.85%。相比基准模型MobileViT_V3, 其计算量降低, 且在Fuzzers等复杂攻击上的识别性能更具鲁棒性。该模型在模型轻量化与检测精度之间取得了有效平衡, 适用于资源受限环境下的网络入侵检测, 具有较高的工程应用价值。
To address the issues of temporal feature loss caused by traffic visualization and the insufficient detection accuracy of lightweight models under complex attacks in network intrusion detection, a lightweight model named MobileViT-AESTF was proposed based on recurrence plot (RP) and an adaptive efficient spatiotemporal fusion (AESTF) module. Utilizing phase space reconstruction technology, the method mapped one-dimensional traffic time series into recursive relationships in a two-dimensional state space via RP, effectively retaining the non-linear temporal features of the traffic. To overcome the insufficient feature capture capability of MobileViT_V3 in processing visualiz
ed traffic, the designed AESTF module comprised an efficient spatiotemporal fusion (ESTF) unit and an adaptive feature exciter (AFE); specifically, the ESTF employed a dual-path heterogeneous attention mechanism to extract spatial and channel features in parallel, while the AFE adaptively enhanced key discriminative features based on a neuronal energy function. Experimental results on the CIC UNSW-NB15 Augmented dataset demonstrate that MobileViT-AESTF achieves an accuracy, recall, and
F
1-score of 99.84%, 99.82%, and 99.85% respectively, while maintaining a low parameter count of 1.04×10
6
. Compared with the baseline MobileViT_V3, the proposed model reduces computational cost and exhibits greater robustness in identifying complex attacks such as Fuzzers. The model achieves an effective balance between lightweight design and detection accuracy, making it suitable for network intrusion detection in resource-constrained environments and offering significant engineering application value.
Black D . Cybercrime will cost $12TN next year, say experts [EB/OL]. ( 2024-01-24 )[ 2025-08-04 ]. https://cybernews.com/news/cybercrime-will-cost-trillions-next-year/ https://cybernews.com/news/cybercrime-will-cost-trillions-next-year/ .
Liao H , Murah M Z , Hasan M K , et al . A survey of deep learning technologies for intrusion detection in internet of things [J]. IEEE Access , 2024 , 12 : 4745 - 4761 .
Han Y L , Han X W . ICPS multi-target constrained comprehensive security control based on DoS attacks energy grading detection and compensation [J]. Journal of Measurement Science and Instrumentation , 2024 , 15 ( 4 ): 518 - 531 .
Demmese F A , Neupane A , Khorsandroo S , et al . Machine learning based fileless malware traffic classification using image visualization [J]. Cybersecurity , 2023 , 6 ( 1 ): 1 - 18 .
刘文琪 , 胡涛 , 闫洁 , 等 . 基于DeepInsight和迁移学习的入侵检测技术 [J]. 工程科学学报 , 2024 , 46 ( 12 ): 2238 - 2245 .
Liu Wenqi , Hu Tao , Yan Jie , et al . Network intrusion detection technology based on DeepInsight and transfer learning [J]. Chinese Journal of Engineering , 2024 , 46 ( 12 ): 2238 - 2245 . (in Chinese)
Li S M , Chai G Z , Wang Y H , et al . CRSF: an intrusion detection framework for industrial internet of things based on pretrained CNN2D-RNN and SVM [J]. IEEE Access , 2023 , 11 : 92041 - 92054 .
Pham V , Seo E , Chung T M . Lightweight convolutional neural network based intrusion detection system [J]. Journal of Communications , 2020 , 15 ( 11 ): 808 - 817 .
姚军 , 孙方超 . 基于MobileViT的轻量型入侵检测模型研究 [J]. 现代电子技术 , 2024 , 47 ( 19 ): 33 - 39 .
Yao Jun , Sun Fangchao . Research on lightweight intrusion detection model based on MobileViT [J]. Modern Electronics Technique , 2024 , 47 ( 19 ): 33 - 39 . (in Chinese)
Tiwari R S , Lakshmi D , Das T K , et al . A lightweight optimized intrusion detection system using machine learning for edge-based IIoT security [J]. Telecommunication Systems , 2024 , 87 ( 3 ): 605 - 624 .
Alshehri M S , Saidani O , Alrayes F S , et al . A self-attention-based deep convolutional neural networks for IIoT networks intrusion detection [J]. IEEE Access , 2024 , 12 : 45762 - 45772 .
Al-Jarrah O Y , El Haloui K , Dianati M , et al . A novel detection approach of unknown cyber-attacks for intra-vehicle networks using recurrence plots and neural networks [J]. IEEE Open Journal of Vehicular Technology , 2023 , 4 : 271 - 280 .
Wadekar S N , Chaurasia A , Mishra A . MobileViTv3: enhanced fusion for mobile vision transformers [C]// Proceedings of the European Conference on Computer Vision , 2023 : 412 - 429 .
Yang L X , Zhang R Y , Li L D , et al . SimAM: A simple, parameter-free attention module for convolutional neural networks [C]// 38th International Conference on Machine Learning , 2021 : 11863 - 11874 .
Wang Y , Li Y S , Wang G , et al . Multi-scale attention network for single image super-resolution [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) , 2024 : 5950 - 5960 .
Canadian Institute for Cybersecurity (CIC) , University of New Brunswick . CIC UNSW-NB15 Augmented Dataset [DB/OL]. [ 2025-09-07 ]. https://unb.ca/cic/datasets/cic-unsw-nb15.html https://unb.ca/cic/datasets/cic-unsw-nb15.html .
Ma N N , Zhang X Y , Zheng H T , et al . Shufflenet v2: Practical guidelines for efficient cnn architecture design [C]// European Conference on Computer Vision (ECCV) , 2018 : 116 - 131 .
Chen X , Liu Z , Wang Y , et al . Efficient mobile transformer for edge-AI security applications [C]// International Conference on Machine Learning , 2023 : 2689 - 2699 .
Howard A G , Zhu M , Chen B , et al . Mobilenets: efficient convolutional neural networks for mobile vision applications [PP/OL]. Vl.arXiv ( 2017-04-17 )[ 2025-09-07 ]. https://arxiv.org/abs/1704.04861 https://arxiv.org/abs/1704.04861 .
Sandler M , Howard A , Zhu M L , et al . MobileNetV2: Inverted residuals and linear bottlenecks [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2018 : 4510 - 4520 .
Howard A , Sandler M , Chen B , et al . Searching for MobileNetV3 [C]// 2019 IEEE/CVF International Conference on Computer Vision(ICCV) , 2019 : 1314 - 1324 .
Mehta S , Rastegari M . Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer [PP/OL]. Vl.arXiv ( 2021-10-05 )[ 2025-09-07 ]. https://arxiv.org/abs/2110.02178 https://arxiv.org/abs/2110.02178 .
Mehta S , Rastegari M . Separable self-attention for mobile vision transformers [PP/OL]. Vl.arXiv ( 2022-06-06 )[ 2025-09-07 ]. https://arxiv.org/abs/2206.02680 https://arxiv.org/abs/2206.02680 .
Vasu P K A , Gabriel J , Zhu J , et al . FastViT: a fast hybrid vision transformer using structural reparameterization [C]// IEEE/CVF International Conference on Computer Vision(ICCV) , 2024 : 5785 - 5794 .
Lu X Y , Suganuma M , Okatani T . SBCFormer: lightweight network capable of full-size imagenet classification at 1 fps on single board computers [C]// IEEE/CVF Winter Conference on Applications of Computer Vision , 2024 : 1123 - 1133 .
Liu C , Zhang H , Wang Z , et al . Squeeze-attention: Lightweight network for real-time intrusion detection [J]. IEEE Transactions on Dependable and Secure Computing , 2024 , 21 ( 3 ): 1987 - 1999 .
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621