Login Register Cart 0
Generic placeholder image

International Journal of Sensors, Wireless Communications and Control

Editor-in-Chief

ISSN (Print): 2210-3279
ISSN (Online): 2210-3287

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

A Pill to Find Them All: IoT Device Behavior Fingerprinting using Capsule Networks

Author(s): Gatha Varma, Ritu Chauhan* and Dhananjay Singh

Volume 12, Issue 2, 2022

Published on: 03 February, 2021

Page: [122 - 131] Pages: 10

DOI: 10.2174/2210327911666210203222153

Price: $65

Abstract

Aim and Background: The aim of this study is the application of novel deep learning technique of capsule networks for device behavior fingerprinting. Device behavior fingerprinting emerged as an important means to characterize the network behavior of connected devices due to the dynamic nature of smart systems. The study of device behavior fingerprinting strategies gave us an insight into the strengths and weaknesses of different machine learning techniques. It also led us to some research questions that we incorporated in the proposed framework. Firstly, we explored the means to improve the efficiency of passive device fingerprinting techniques. Secondly, we needed to address the privacy concerns that arise from the creation and maintenance of device fingerprints.

Objective: To our best knowledge, this is the first time that device for fingerprints had been generated in the form of images. The use of device fingerprints in image form best utilized the object recognition capabilities of capsule networks.

Method: We designed a novel method to classify and save the network behaviour of IoT devices that are connected to a network. The proposed model was based on a two-fold innovation of the generation of unique images based on packet parameters of device transmissions, and the design of a model that could carry out efficient and accurate classification of device vendors based on their network behavior.

Results and Conclusion: The generation of unique images offered a big advantage of saving the memory of the system. While a packet capture file may take around 150kb or more, the generated images were as small as the order of 2kb. For a smart system made up of thousands of devices, the order of memory space saved would become significant. Furthermore, since the algorithm of image generation could be customized by the network administrators, the images cannot be reverse- engineered by potential attackers, thereby assuring a secure way to save device behavior fingerprints. The developed model has compiled over 500 epochs that roughly translated to 100 minutes and gave the accuracy of the order of 92%. This was the first time that device network behaviour has been translated into an image and tested through classification using capsule networks. The translation of captured packet flows to black and white images not only saved on memory space but also provided a safeguard against reverse engineering by potential attackers. There is a vast scope to further use of this strategy to develop more complex device fingerprinting methods.

Keywords: Internet of Things, device behavior fingerprinting, capsule network, CNN, image generation, smart systems.

« Previous Next »
Graphical Abstract

[1]
Voas J, Agresti B, Laplante, P. A. A closer look at IoT 's things. IT Profess 2018, 20, 11-14.
[http://dx.doi.org/10.1109/MITP.2018.032501741]
[2]
Chui M, Löffler M, Roberts R. The internet of things. McKinsey Q. 2010, 2, 1–9.
[3]
Tanwar G, Chauhan R, Yafi E. Artycul: A privacy-preserving ml-driven framework to determine the popularity of a cultural exhibit on display. Sensors 2021; 21(4): 1527.
[http://dx.doi.org/10.3390/s21041527]
[4]
Tanwar G, Chauhan R, Singh M, Singh D. Pre-emption of affliction severity using hrv measurements from a smart wearable; case-study on SARS-cov-2 symptoms. Sensors 2020; 20(24): 7068.
[http://dx.doi.org/10.3390/s20247068]
[5]
Hassija V, Chamola V, Saxena V, Jain D, Goyal P, Sikdar B. A Survey on IoT security: Application areas, security threats, and solution architectures. IEEE Access 2019, 7,82721-43.
[6]
Uluagac AS, Radhakrishnan SV, Corbett C, Baca A, Beyah R. A passive technique for fingerprinting wireless devices with wiredside observations. Communications and Network Security (CNS), 2013 IEEE Conference on. IEEE, 2013, pp. 305–313.
[7]
Blythe JM, Johnson SD, Manning M. What is security worth to consumers? Investigating willingness to pay for secure Internet of Things devices. Crime Sci 2020; 9: 1.
[http://dx.doi.org/10.1186/s40163-019-0110-3]
[8]
Tanwar G, Chauhan R, Singh D (2020) Ensuring privacy-aware data release: An analysis of applicability of privacy enhancing techniques to real-world datasets. 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) 2020.
[9]
The hacker news [homepage on the internet] Casino gets hacked through its internet-connected fish tank thermometer [updated 2018 April 16; cited 2020 July 27] Available from: https://thehackernews.com/2018/04/iot-hacking-thermometer.html
[10]
Jang-Jaccard, Julian & Nepal, Surya. (2014). A survey of emerging threats in cybersecurity. J Comput Syst Sci 2014; 80(5): 973- 93.80.
[http://dx.doi.org/10.1016/j.jcss.2014.02.005.]
[11]
Bendovschi A. Cyber-Attacks: Trends, patterns and security countermeasures. Procedia Economics and Finance 2015; 8: 24-31.
[12]
Tanwar G, Chauhan R, Singh D (2020) User Privacy in Smart Systems: Recent Findings and Countermeasures. Proceedings of the International Conference on Innovative Computing & Communications (ICICC) 2020 April 5; India: ICICC 2020.
[13]
Miettinen M, Marchal S, Hafeez I, Frassetto T, Asokan N, Sadeghi A-R, Tarkoma S. IoT sentinel demo: Automated devicetype identification for security enforcement in IoT 2017; 2017: 2511-2514. 10.1109/ICDCS.2017.284
[14]
Xu Q, Zheng R, Saad W, Han Z. Device fingerprinting in wireless networks: Challenges and opportunities. IEEE Comm Surv Tutor 2018; 1: 94-104.
[15]
Cunche M, Kaafar M-A, Boreli R. Linking wireless devices using information contained in wifi probe requests. Pervasive Mobile Comput 2014; 11: 56-69.
[16]
Miettinen M, Marchal S, Hafeez I, Asokan N, Sadeghi A, Tarkoma S. Iot sentinel: Automated device-type identification for security enforcement in iot. CoRR, vol. abs/1611.04880, 2016.
[17]
Thangavelu V, Divakaran DM, Sairam R, Bhunia S, Gurusamy M. DEFT: A distributed IoT fingerprinting technique (IEEE IoT Journal). 2018. 10.1109/JIOT.2018.2865604.
[18]
Luo Y, Hu H, Wen Y, Tao D. Transforming device fingerprinting for wireless security via online multi-task metric learning. IEEE Internet of Things J. 2019. PP. 1-1. 10.1109/JIOT.2019.2946500
[19]
Chauhan R, Kaur H, Chang V. Advancement and applicability of classifiers for variant exponential model to optimize the accuracy for deep learning. J Ambient Intell Human Comput 2017.
[http://dx.doi.org/10.1007/s12652-017-0561-x]
[20]
Chauhan R, Kaur H. A Feature Based Reduction technique on Large Scale Databases. Int J Data Analysis Techand Strategies 2017; 9(3): 207-21.
[http://dx.doi.org/10.1504/IJDATS.2017.086630]
[21]
Agadakos I, Anantharaman P, Ciocarlie G, Copos B, Emmi M, Lepoint T, Lindqvist U, Locasto M, Song L. Securing smart cities: Implications and challenges. [Internet]. Modeling and design of secure Internet of things. Wiley; 2020. p. 185–215. Available from:
[http://dx.doi.org/10.1002/9781119593386.ch9]
[22]
Yao H, Gao P, Wang J, Zhang P, Jiang C, Han Z. Capsule network assisted IoT traffic classification mechanism for smart cities. IEEE Internet Things J 2019; 6(5): 7515-25.
[http://dx.doi.org/10.1109/JIOT.2019.2901348]
[23]
Sabour S, Frosst N, Hinton GE. Dynamic routing between capsules. Proc. NIPS, Mar. 2017, pp. 3859–3869
[24]
Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks? Proc. Adv. Neural Inf. Process. Syst., Nov. 2014; 6 :3320–3328.
[25]
Sandhya A, Aneja N, Islam MS. IoT device fingerprint using deep learning. 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS); 2018 Oct 29-31; Los Angeles, CA, USA; IEEE 2019.
[26]
Himblot T. py-image-dataset-generator: Get a large image dataset with minimal effort by grabbing image through the web and generate new ones by image augmentation. [updated 2018 April 16; cited 2020 August 27] Available from: https://github.com/tomahim/py-image-dataset-generator
[27]
Scapy Project [homepage on the internet] Scapy Project [updated 2020 /July 16; cited 2020 July 27] Available from: https://scapy.net/
[28]
Boissonnat J-D, Dyer R, Ghosh A. Constructing stable delaunay triangulations. Research Report RR-8275, INRIA, 2013.

Rights & Permissions Print Cite
Article Metrics
15
© 2024 Bentham Science Publishers | Privacy Policy