Application of reliefF feature selection in trust evaluation of user abnormal behavior

Xiangyu Liu; Yuwei Li

doi:10.1117/12.2635939

5 May 2022 Application of reliefF feature selection in trust evaluation of user abnormal behavior

Xiangyu Liu, Yuwei Li

Proceedings Volume 12245, International Conference on Cryptography, Network Security, and Communication Technology (CNSCT 2022); 122450H (2022) https://doi.org/10.1117/12.2635939
Event: International Conference on Cryptography, Network Security, and Communication Technology (CNSCT 2022), 2022, Sanya, China

Abstract

In recent years, in the field of internal network threat analysis, some scholars have proposed a user behavior evaluation method based on analytic hierarchy process (AHP)^[1]. The method is mainly to give weight to the user behavior evidence after standardization, and realize the evaluation of user behavior according to the weight. In the early stage, some scholars assigned the weight of evidence by expert evaluation method, but it is difficult to avoid the problems of excessive subjectivity and unable to adapt to data changes. This paper combines the reliefF feature selection algorithm with the weight assignment in user behavior evaluation to ensure that the weight is matched with the data and obtain the evidence weight that meets the actual requirements.

Citation Download Citation

Xiangyu Liu and Yuwei Li "Application of reliefF feature selection in trust evaluation of user abnormal behavior", Proc. SPIE 12245, International Conference on Cryptography, Network Security, and Communication Technology (CNSCT 2022), 122450H (5 May 2022); https://doi.org/10.1117/12.2635939

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