提出了一种基于CBAMTL-MobileNet V3的车载网络入侵检测方法。该方法使用轻量级模型MobileNet V3,减少其层数加快模型的训练和检测速度;将模型中的SE模块置换为注意力模块(CBAM)使模型更聚焦于特定特征,提高特征提取能力,进而提高检测攻击的精确度;引入迁移学习对模型权重进行微调,减少参数和内存资源的消耗,缩短了训练时间,使模型表现出更快的运算速度。仿真结果表明:所提模型的各项检测指标都优于MobileNet V3模型。与其他模型相比,所提模型既具备轻量级模型的高效性,同时又高于其他复杂模型的检测精度,识别各类别攻击的性能最优。
Abstract
A vehicle network intrusion detection method is proposed based on CBAMTL-MobileNet V3. The lightweight MobileNet V3 model is used, and reduced its layers to improve both training and detection speeds. The squeeze-and-excitation (SE) modules in the model are replaced with convolutional block attention module (CBAM) to focus the model more on specific features, enhancing feature extraction capabilities and consequently improving the accuracy of attack detection. Transfer learning is introduced to fine-tune the model weights, reducing parameter and memory resource consumption, thereby shortening the training time and improving the computational speed of the model. Simulation results indicate that the proposed model is better than the MobileNet V3 model in various detection indexes. Compared with other models,the proposed model exhibits both the efficiency of a lightweight model and higher detection accuracy than other complex models, making it the optimal performer in recognizing various types of attacks.
关键词
无线电计量 /
机器视觉;入侵检测;深度学习;轻量级模型;车载网络
Key words
radio metrology /
machine vision /
intrusion detection /
deep learning /
lightweight model /
vehicle network
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］姚海龙, 闫巧. 面向车联网增值服务的匿名认证协议的密码分析与设计 ［J］. 计算机研究与发展, 2022, 59(2): 440-451.
YAO H L, YAN Q. Cryptanalysis and Design of Anonymous Authentication Protocol for Value-Added Services in Internet of Vehicles ［J］. Journal of Computer Research and Development, 2022, 59(2): 440-451.
［2］JIN S, CHUNG J G, XU Y. Signature-based intrusion detection system (IDS) for in-vehicle CAN bus network［C］//IEEE. 2021 IEEE International Symposium on Circuits and Systems (ISCAS). 2021: 1-5.
［3］ZENG W, KHALID M A S, CHOWDHURY S. In-vehicle networks outlook: Achievements and challenges ［J］. IEEE Communications Surveys & Tutorials, 2016, 18(3): 1552-1571.
［4］NING J, WANG J, LIU J, et al. Attacker identification and intrusion detection for in-vehicle networks ［J］. IEEE communications letters, 2019, 23(11): 1927-1930.
［5］MISHRA A, GUPTA N, GUPTA B B. Defense mechanisms against DDoS attack based on entropy in SDN-cloud using POX controller ［J］. Telecommunication systems, 2021, 77: 47-62.
［6］LO W, ALQAHTANI H, THAKUR K, et al. A hybrid deep learning based intrusion detection system using spatial-temporal representation of in-vehicle network traffic ［J］. Vehicular Communications, 2022, 35: 100471.
［7］GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks ［J］. Pattern recognition, 2018, 77: 354-377.
［8］WANG W, SHENG Y, WANG J, et al. HAST-IDS: Learning hierarchical spatial-temporal features using deep neural networks to improve intrusion detection ［J］. IEEE access, 2017, 6: 1792-1806.
［9］HU R, WU Z, XU Y, et al. Multi-attack and multi-classification intrusion detection for vehicle-mounted networks based on mosaic-coded convolutional neural network ［J］. Scientific Reports, 2022, 12(1): 6295.
［10］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). 2018: 1-6.
［11］SONG H M, WOO J, KIM H K. In-vehicle network intrusion detection using deep convolutional neural network ［J］. Vehicular Communications, 2020, 21: 100198.
［12］DESTA A K, OHIRA S, ARAI I, et al. Rec-CNN: In-vehicle networks intrusion detection using convolutional neural networks trained on recurrence plots ［J］. Vehicular Communications, 2022, 35: 100470.
［13］DU W, WANG Y, QIAO Y. Recurrent spatial-temporal attention network for action recognition in videos ［J］. IEEE Transactions on Image Processing, 2017, 27(3): 1347-1360.
［14］朱张莉, 饶元, 吴渊,等. 注意力机制在深度学习中的研究进展 ［J］. 中文信息学报, 2019,33(6): 1-11.
ZHU Z L, RAO Y, WU Y, et al. Research Progress on Attention Mechanisms in Deep Learning ［J］. Journal of Chinese Information Processing, 2019, 33(6): 1-11.
［15］吴忠强, 卢雪琴. 基于深度迁移学习和LSTM网络的微电网故障诊断 ［J］. 计量学报, 2023, 44(4): 582-590.
WU Z Q, LU X Q. Microgrid Fault Diagnosis Based on Deep Transfer Learning and LSTM Network ［J］. Acta Metrologica Sinica, 2023, 44(4): 582-590.
［16］张典范, 杨镇豪, 程淑红. 基于ResNet50与迁移学习的轮毂识别 ［J］. 计量学报, 2022, 43(11): 1412-1417.
ZHANG D F, YANG Z H, CHENG S H. Wheel Hub Recognition Based on ResNet50 and Transfer Learning ［J］. Acta Metrologica Sinica, 2022, 43(11): 1412-1417.
［17］LEE H, JEONG S H, KIM H K. OTIDS: A novel intrusion detection system for in-vehicle network by using remote frame［C］//IEEE. 2017 15th Annual Conference on Privacy, Security and Trust (PST). 2017: 57-5709.
［18］AKSU D, AYDIN M A. MGA-IDS: Optimal feature subset selection for anomaly detection framework on in-vehicle networks-CAN bus based on genetic algorithm and intrusion detection approach ［J］. Computers & Security, 2022, 118: 102717.
［19］ALQAHTANI H, KUMAR G. A deep learning-based intrusion detection system for in-vehicle networks ［J］. Computers and Electrical Engineering, 2022, 104: 108447.
［20］蒋玉长, 徐洋, 李克资, 等. 基于深度学习的轻量级车载网络入侵检测方法 ［J］. 计算机工程与应用, 2023, 59(22): 284-292.
JIANG Y C, XU Y, LI K Z, et al. Lightweight In-vehicle Network Intrusion Detection Method based on Deep Learning ［J］. Computer Engineering and Applications, 2023, 59(22): 284-292.
基金
省级重点实验室绩效补助经费项目(22567612H)
PDF(606 KB)
