Research on traffic attack behavior detection for IoT device security

ZhiLiang Xiao

doi:10.1117/12.2685487

28 July 2023 Research on traffic attack behavior detection for IoT device security

ZhiLiang Xiao

Proceedings Volume 12716, Third International Conference on Digital Signal and Computer Communications (DSCC 2023); 127161V (2023) https://doi.org/10.1117/12.2685487
Event: Third International Conference on Digital Signal and Computer Communications (DSCC 2023), 2023, Xi'an, China

Abstract

Compared with the Internet, the IoT has more potential security issues and the traffic is exposed to greater security risks. The number of IoT devices is large, and the generalization performance and accuracy of current traffic attack detection algorithms are not satisfactory. In order to improve the efficiency of traffic detection, the Cross validation feature selection random forest algorithm (CVFSRF) is used to select the effective features for different types of IoT devices, taking into account the characteristics of IoT devices themselves. information for different types of IoT devices to train the detection model. The traffic detection uses a semi-supervised learning strategy to improve the detection accuracy by optimizing the type and number of individual learners through integrated learning. After conducting simulation experiments, the average detection accuracy of the algorithm is 99.52% and the detection time is 1.26s, which can efficiently and accurately detect traffic attacks on different IoT devices to ensure device security.

Citation Download Citation

ZhiLiang Xiao "Research on traffic attack behavior detection for IoT device security", Proc. SPIE 12716, Third International Conference on Digital Signal and Computer Communications (DSCC 2023), 127161V (28 July 2023); https://doi.org/10.1117/12.2685487

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