期刊
DECISION SUPPORT SYSTEMS
卷 55, 期 1, 页码 314-325出版社
ELSEVIER
DOI: 10.1016/j.dss.2013.01.020
关键词
Shilling attacks detection; Collaborative filtering; Recommender systems
类别
资金
- National Science Council of the Taiwan (Republic of China) [NSC 99-2410-H-008-032]
- Ministry of Education (MOE) Program for Aiming for the Top Universities [101G904-4]
Recommender systems are widely deployed to provide user purchasing suggestion on eCommerce websites. The technology that has been adopted by most recommender systems is collaborative filtering. However, with the open nature of collaborative filtering recommender systems, they suffer significant vulnerabilities from being attacked by malicious raters, who inject profiles consisting of biased ratings. In recent years, several attack detection algorithms have been proposed to handle the issue. Unfortunately, their applications are restricted by various constraints. PCA-based methods while having good performance on paper, still suffer from missing values that plague most user-item matrixes. Classification-based methods require balanced numbers of attacks and normal profiles to train the classifiers. The detector based on SPC (Statistical Process Control) assumes that the rating probability distribution for each item is known in advance. In this research, Beta-Protection ( beta P) is proposed to alleviate the problem without the abovementioned constraints. beta P grounds its theoretical foundation on Beta distribution for easy computation and has stable performance when experimenting with data derived from the public websites of MovieLens. (C) 2013 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据