Fraud attack behavior analysis based on collaborative filtering algorithm of personalized recommender system

Laihua Chang; Chong Wang

doi:10.1117/12.2657220

28 November 2022 Fraud attack behavior analysis based on collaborative filtering algorithm of personalized recommender system

Laihua Chang, Chong Wang

Author Affiliations +

Proceedings Volume 12503, International Conference on Network Communication and Information Security (ICNCIS 2022); 125030V (2022) https://doi.org/10.1117/12.2657220
Event: International Conference on Network Communication and Information Security (ICNCIS 2022), 2022, Qingdao, China

Abstract

Personalized recommendation system is divided into offline system and online system, the two are interconnected and cooperate with each other, and there are some problems in the development process. In response to the above problems, user-led recommendation and project-guided recommendation can be improved respectively. In addition, a good, personalized recommendation system is inseparable from excellent design. It is mainly divided into four management systems: source data management, ETL management, data policy management and cluster management, with the emphasis on data policy management. The research shows that the attack model and attack cost of fraud attack have different effects on the attack performance. In response to this problem, the performance of the collaborative filtering algorithm based on singular value segmentation SVD under different attack models is analyzed experimentally, and the impact of different filling scales and attack scales on attack efficiency is analyzed with three evaluation parameters.

Citation Download Citation

Laihua Chang and Chong Wang "Fraud attack behavior analysis based on collaborative filtering algorithm of personalized recommender system", Proc. SPIE 12503, International Conference on Network Communication and Information Security (ICNCIS 2022), 125030V (28 November 2022); https://doi.org/10.1117/12.2657220

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