Intelligent device identification based on traffic time-series features

Senhao Zhu; Xiaofeng Lu

doi:10.1117/12.2684012

14 June 2023 Intelligent device identification based on traffic time-series features

Senhao Zhu, Xiaofeng Lu

Proceedings Volume 12708, 3rd International Conference on Internet of Things and Smart City (IoTSC 2023）; 1270822 (2023) https://doi.org/10.1117/12.2684012
Event: 3rd International Conference on Internet of Things and Smart City (IoTSC 2023）, 2023, Chongqing, China

Abstract

With the rapid proliferation of Internet of Things (IoT) devices, the security risks associated with IoT devices are increasing rapidly. It is necessary to identify various types of intelligent IoT devices. This paper proposes an algorithm based on time series features to group and merge data packets and calculate statistical features to identify IoT devices. The protocol features in the response message header of IoT devices are taken into account. Furthermore, with the feature selection technique of maximum information coefficient and information gain, important feature subsets are selected by considering both the network properties and security properties of the features. Finally, based on machine learning algorithms, traffic features of smart devices are modeled to achieve identification of different IoT devices. The experimental results show that the proposed method has good adaptability and achieved higher identification accuracy in two different public datasets.

Citation Download Citation

Senhao Zhu and Xiaofeng Lu "Intelligent device identification based on traffic time-series features", Proc. SPIE 12708, 3rd International Conference on Internet of Things and Smart City (IoTSC 2023）, 1270822 (14 June 2023); https://doi.org/10.1117/12.2684012

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available