Enhancing ECU identification security in CAN networks using distortion modeling and neural networks

被引:1
|
作者
Hafeez, Azeem [1 ]
Malik, Hafiz [1 ]
Irtaza, Aun [1 ]
Uddin, Md Zia [2 ]
Noori, Farzan M. [3 ]
机构
[1] Univ Michigan Dearborn, Dept Elect & Comp Engn, Dearborn, MI USA
[2] SINTEF Digital, Dept Sustainable Commun Technol, Oslo, Norway
[3] Univ Oslo, Dept Informat, Oslo, Norway
来源
FRONTIERS IN COMPUTER SCIENCE | 2024年 / 6卷
基金
美国国家科学基金会;
关键词
intrusion detection system; electronic control unit (ECU); controller area network (CAN); machine learning; artificial neural network (ANN); digital-to-analog converter (DAC); performance matrix (PM); SOLAR GRADE SILICON; INTRUSION DETECTION; CONTROLLER; CHALLENGES; VEHICLES; BEHAVIOR;
D O I
10.3389/fcomp.2024.1392119
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
A novel technique for electronic control unit (ECU) identification is proposed in this study to address security vulnerabilities of the controller area network (CAN) protocol. The reliable ECU identification has the potential to prevent spoofing attacks launched over the CAN due to the lack of message authentication. In this regard, we model the ECU-specific random distortion caused by the imperfections in the digital-to-analog converter and semiconductor impurities in the transmitting ECU for fingerprinting. Afterward, a 4-layered artificial neural network (ANN) is trained on the feature set to identify the transmitting ECU and the corresponding ECU pin. The ECU-pin identification is also a novel contribution of this study and can be used to prevent voltage-based attacks. We have evaluated our method using ANNs over a dataset generated from 7 ECUs with 6 pins, each having 185 records, and 40 records for each pin. The performance evaluation against state-of-the-art methods revealed that the proposed method achieved 99.4% accuracy for ECU identification and 96.7% accuracy for pin identification, which signifies the reliability of the proposed approach.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] Person Identification by Footstep Sound Using Convolutional Neural Networks
    Algermissen, Stephan
    Hoernlein, Max
    APPLIED MECHANICS, 2021, 2 (02): : 257 - 273
  • [32] Identification of probe request attacks in WLANs using neural networks
    Deepthi N. Ratnayake
    Hassan B. Kazemian
    Syed A. Yusuf
    Neural Computing and Applications, 2014, 25 : 1 - 14
  • [33] Enhancing IoT security: a collaborative framework integrating federated learning, dense neural networks, and blockchain
    Nazir, Ahsan
    He, Jingsha
    Zhu, Nafei
    Anwar, Muhammad Shahid
    Pathan, Muhammad Salman
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2024, 27 (06): : 8367 - 8392
  • [34] Wildland Fire Spread Modeling Using Convolutional Neural Networks
    Jonathan L. Hodges
    Brian Y. Lattimer
    Fire Technology, 2019, 55 : 2115 - 2142
  • [35] Modeling Maximum Tsunami Heights Using Bayesian Neural Networks
    Song, Min-Jong
    Cho, Yong-Sik
    ATMOSPHERE, 2020, 11 (11) : 1 - 13
  • [36] Modeling Fused Filament Fabrication using Artificial Neural Networks
    Oehlmann, Paul
    Osswald, Paul
    Blanco, Juan Camilo
    Friedrich, Martin
    Rietzel, Dominik
    Witt, Gerd
    PRODUCTION ENGINEERING-RESEARCH AND DEVELOPMENT, 2021, 15 (3-4): : 467 - 478
  • [37] Enhancing geothermal petrography with convolutional neural networks
    Padrique, Maria Gracia C.
    Narag, Mark Jeremy G.
    Fernando, Allan Gil S.
    Soriano, Maricor N.
    GEOTHERMICS, 2025, 127
  • [38] Hybrid thermal modeling of additive manufacturing processes using physics-informed neural networks for temperature prediction and parameter identification
    Liao, Shuheng
    Xue, Tianju
    Jeong, Jihoon
    Webster, Samantha
    Ehmann, Kornel
    Cao, Jian
    COMPUTATIONAL MECHANICS, 2023, 72 (03) : 499 - 512
  • [39] Modeling the butterfly behavior of SMA actuators using neural networks
    Hmede, Rodayna
    Chapelle, Frederic
    Lapusta, Yuri
    COMPTES RENDUS MECANIQUE, 2022, 350 (01): : 143 - 157
  • [40] Modeling Fused Filament Fabrication using Artificial Neural Networks
    Paul Oehlmann
    Paul Osswald
    Juan Camilo Blanco
    Martin Friedrich
    Dominik Rietzel
    Gerd Witt
    Production Engineering, 2021, 15 : 467 - 478