Reliable Identification of IoT Devices from Passive Network Traffic Analysis: Requirements and Recommendations

被引:1
|
作者
Andrews, Ashley [1 ]
Oikonomou, George [1 ]
Armour, Simon [1 ]
Thomas, Paul [1 ]
Cattermole, Thomas [2 ]
机构
[1] Univ Bristol, Bristol, Avon, England
[2] UCL, London, England
关键词
Internet of Things (IoT); Device Identification; Firmware versions; Machine Learning (ML);
D O I
10.1109/WF-IOT58464.2023.10539470
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Internet of Things (IoT) devices are becoming more widespread in networks and can give malicious actors new vectors to compromise networks. Of particular concern are devices running out-of-date firmware versions with known vulnerabilities. Securing real-world IoT networks therefore relies on knowing what devices are on a network and knowing what specific firmware versions they are running. At present, though, commercial solutions that include IoT device identification are not reliable at this level of granularity, and the academic literature has largely ignored the problem. In this paper, we highlight the shortcomings present in current IoT device identification and use these observations to develop a set of lab requirements. We then present our own lab setup for providing reliable real-world IoT device identification that meets this set of requirements. Building on this work, we develop a schema for documenting device versions and event histories that accompany network packet traces as metadata.
引用
收藏
页数:6
相关论文
共 50 条
  • [31] IoT Wireless Intrusion Detection and Network Traffic Analysis
    Ponnusamy V.
    Yichiet A.
    Jhanjhi N.Z.
    Humayun M.
    Almufareh M.F.
    Computer Systems Science and Engineering, 2021, 40 (03): : 865 - 879
  • [32] A machine learning based framework for IoT devices identification using web traffic
    Hussain, Sajjad
    Aslam, Waqar
    Mehmood, Arif
    Choi, Gyu Sang
    Ashraf, Imran
    PEERJ COMPUTER SCIENCE, 2024, 10
  • [33] Identification of IoT Device From Network Traffic Using Artificial Intelligence Based Capsule Networks
    H. Azath
    M. Devi Mani
    G. K. D. Prasanna Venkatesan
    D. Sivakumar
    J. P. Ananth
    S. Kamalraj
    Wireless Personal Communications, 2022, 123 : 2227 - 2243
  • [34] Identifying SH-IoT devices from network traffic characteristics using random forest classifier
    Chowdhury, Rajarshi Roy
    Idris, Azam Che
    Abas, Pg Emeroylariffion
    WIRELESS NETWORKS, 2023, 30 (1) : 405 - 419
  • [35] Identifying SH-IoT devices from network traffic characteristics using random forest classifier
    Rajarshi Roy Chowdhury
    Azam Che Idris
    Pg Emeroylariffion Abas
    Wireless Networks, 2024, 30 : 405 - 419
  • [36] Identification of IoT Device From Network Traffic Using Artificial Intelligence Based Capsule Networks
    Azath, H.
    Mani, M. Devi
    Venkatesan, G. K. D. Prasanna
    Sivakumar, D.
    Ananth, J. P.
    Kamalraj, S.
    WIRELESS PERSONAL COMMUNICATIONS, 2022, 123 (03) : 2227 - 2243
  • [37] Network Traffic Modeling For IoT-device Re-identification
    Najari, Naji
    Berlemont, Samuel
    Lefebvre, Gregoire
    Duffner, Stefan
    Garcia, Christophe
    2020 INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2020), 2020, : 162 - 167
  • [38] Locality-Sensitive IoT Network Traffic Fingerprinting for Device Identification
    Charyyev, Batyr
    Gunes, Mehmet Hadi
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (03): : 1272 - 1281
  • [39] Analysis on network performance of container virtualization on IoT devices
    Lee, Kyungwoon
    Kim, Hyunjin
    Kim, Beomsu
    Yoo, Chuck
    2017 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC), 2017, : 35 - 37
  • [40] A Group-Based IoT Devices Classification Through Network Traffic Analysis Based on Machine Learning Approach
    Bassene, Avewe
    Gueye, Bamba
    TOWARDS NEW E-INFRASTRUCTURE AND E-SERVICES FOR DEVELOPING COUNTRIES, AFRICOMM 2020, 2021, 361 : 185 - 202