Re-scale AdaBoost for attack detection in collaborative filtering recommender systems
Re-scale AdaBoost for attack detection in collaborative filtering recommender systems
复制标题
DOI：
10.1016/j.knosys.2016.02.008
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Zhihai Yang;Lin Xu;Zhongmin Cai;Zongben Xu
中科院分区：
文献类型：
--
作者：
Zhihai Yang;Lin Xu;Zhongmin Cai;Zongben Xu
协同过滤推荐系统（CFRSs）是电子商务系统成功的关键组成部分。然而，由于cfrs的开放性，它极易受到“先令”攻击或“配置文件注入”攻击。由于攻击者的规模通常远远小于真正的用户，传统的基于监督学习的检测方法可能过于“沉闷”，无法处理这种不平衡的分类。在本文中，我们从以下两个方面提高了检测性能。首先，我们根据不同攻击模型的统计特性，从用户配置文件中提取精心设计的特征，使难检测场景变得更容易执行。然后，参考重尺度增强（rboost）和AdaBoost的一般思想，我们将AdaBoost的一种变体，称为重尺度AdaBoost （RAdaBoost）作为我们基于提取的特征的检测方法。最后，在MovieLens-100K数据集上进行了一系列实验，以证明RAdaBoost优于其他竞争技术（如SVM、kNN和AdaBoost）。
Collaborative filtering recommender systems (CFRSs) are the key components of successful E-commerce systems. However, CFRSs are highly vulnerable to “shilling” attacks or “profile injection” attacks due to its openness. Since the size of attackers is usually far smaller than genuine users, conventional supervised learning based detection methods could be too “dull” to handle such imbalanced classification. In this paper, we improve detection performance from following two aspects. Firstly, we extract well-designed features from user profiles based on the statistical properties of the diverse attack models, making hard detection scenarios become easier to perform. Then, refer to the general idea of re-scale Boosting (RBoosting) and AdaBoost, we apply a variant of AdaBoost, called the re-scale AdaBoost (RAdaBoost) as our detection method based on the extracted features. Finally, a series of experiments on the MovieLens-100K dataset are conducted to demonstrate the outperformance of RAdaBoost over other competing techniques such as SVM, kNN and AdaBoost.