基于评分离散度的托攻击检测算法

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (03): 554-562.

基于评分离散度的托攻击检测算法

贾俊杰，段超强

（西北师范大学计算机科学与工程学院，甘肃兰州 730070）

收稿日期:2020-08-16 修回日期:2020-11-26 接受日期:2022-03-25 出版日期:2022-03-25 发布日期:2022-03-24
基金资助:
国家自然科学基金（61967013）；甘肃省高等学校创新能力提升项目（2019A-006）

A shilling attack detection algorithm based on score dispersion

JIA Jun-jie,DUAN Chao-qiang

(School of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070,China)

Received:2020-08-16 Revised:2020-11-26 Accepted:2022-03-25 Online:2022-03-25 Published:2022-03-24

摘要/Abstract

摘要： 检测托攻击的本质是对真实用户和虚假用户进行分类，现有的检测算法对于具有选择项的流行攻击、段攻击等攻击方式的检测鲁棒性较差。针对这一问题，通过分析真实用户和虚假用户的评分分布情况，结合ID3决策树提出基于用户评分离散度的托攻击检测Dispersion-C算法。算法通过用户评分极端评分比、去极端评分方差和用户评分标准差3个特征衡量用户评分离散度，并将其作为ID3决策树算法的分类特征，根据不同特征的信息增益选择特征作为分类属性，训练分类器。实验结果表明，Dispersion-C算法对各类托攻击均有良好的检测效果，具有较好的鲁棒性。

关键词: 推荐系统, 托攻击检测, 评分离散度, 决策树

Abstract: The essence of detecting shilling attacks is to classify real users and fake users. The existing detection algorithms have poor detection robustness against bandwagon attacks and segment attacks with options. To solve this problem, by analyzing the different distributions of ratings of real users and fake users, combined with ID3 decision tree, a shilling attack detection algorithm based on user score dispersion is proposed. The algorithm measures the dispersion of user scores by using three features: extreme score ratio, de-extreme score variance, and user score standard deviation, and uses it as the classification feature of the ID3 decision tree algorithm. According to the information gain of different features, the feature is selected as the classification attribute, and the classifier is trained. Experiments show that the algorithm has a good detection effect on all kinds of shilling attacks, and has good robustness.

Key words: recommendation system, shilling attack detection, score dispersion, decision tree

贾俊杰, 段超强. 基于评分离散度的托攻击检测算法[J]. 计算机工程与科学, 2022, 44(03): 554-562.

JIA Jun-jie, DUAN Chao-qiang. A shilling attack detection algorithm based on score dispersion[J]. Computer Engineering & Science, 2022, 44(03): 554-562.

参考文献［22］

［1］	Mu R H,Zeng X Q.Collaborative filtering recommendation algorithm based on knowledge graph［J］.Mathematical Problems in Engineering,2018(4):1-11.
［2］	Ren Y,Li G,Zhang J,et al.The efficient imputation method for neighborhood-based collaborative filtering［C］∥Proc of the 21st ACM International Conference on Information and Knowledge Management,2012:684-693.
［3］	Ren Y,Li G,Zhou W.Learning rating patterns for top-N recommendations［C］∥Proc of 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining,2012:472-479.
［4］	Yang Z H, Cai Z M. Detecting abnormal profiles in collaborative filtering recommender systems［J］.Journal of Intelligent Information Systems,2017,48:499-518.
［5］	Gunes I,Kaleli C,Bilge A,et al.Shilling attacks against re- commender systems:A comprehensive survey［J］.Artificial Intelligence Review,2014,42(4):767-799.
［6］	Gao M, Yuan Q, Ling B,et al.Detection of abnormal item based on time intervals for recommender systems［J］.The Scientific World Journal,2014,2014:845-897.
［7］	Lee J S,Zhu D.Shilling attack detection—A new approach for a trustworthy recommender system［J］.INFORMS Journal on Computing,2012,24(1):117-131.
［8］	Rashid A M,Karypis G,Riedl J.Influence in ratings-based recommender systems:An algorithm-independent approach ［C］∥Proc of the 2005 SIAM International Conference on Data Mining,2005:556-560.
［9］	Chirita P A,Nejdl W,Zamfir C.Preventing shilling attacks in online recommender systems［C］∥Proc of the 7th Annual ACM International Workshop on Web Information and Data Management,2005:67-74.
［10］	Burke R,Mobasher B,Williams C,et al.Classification features for attack detection in collaborative recommender systems［C］∥Proc of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2006:542-547.
［11］	Burke R, Mobasher B, Williams C, et al.Detecting profile injection attacks in collaborative recommender systems［C］∥Proc of the 8th IEEE International Conference on E-Commerce Technology and the 3rd IEEE International Conference on Enterprise Computing,E-Commerce,and E-Services,2006:23.
［12］	Bryan K,O’Mahony M,Cunningham P.Unsupervised retrieval of attack profiles in collaborative recommender systems ［C］∥Proc of the 2008 ACM Conference on Recommender Systems,2008:155-162.
［13］	Li Wen-tao,Gao Min,Li Hua,et al.An shilling attack detection algorithm based on popularity degree features［J］.Acta Automatica Sinica,2015,41(9):1563-1576.(in Chinese)
［14］	Mehta B. Unsupervised shilling detection for collaborative filtering［C］∥Proc of the 22nd AAAI Conference on Artificial Intelligence,2007:1402-1407.
［15］	Mehta B,Nejdl W.Unsupervised strategies for shilling detection and robust collaborative filtering［J］.User Modeling and User-Adapted Interaction,2009,19(1):65-97.
［16］	Li Cong,Luo Zhi-gang. Detecting shilling attacks in recommender systems based on non-random-missing mechanism［J］.Acta Automatica Sinica,2013,39(10):1681-1690.(in Chinese)
［17］	Cao J,Wu Z,Mao B,et al.Shilling attack detection utilizing semi-supervised learning method for collaborative recommender system［J］.World Wide Web,2013,16(5):729-748.
［18］	Wu Z, Cao J, Mao B, et al.Semi-SAD:Applying semi- supervised learning to shilling attack detection ［C］∥Proc of the 5th ACM Conference on Recommender Systems,2011:289-292.
［19］	MoviesLens dataset［EB/OL］.［2020-06-15］.http://www.cs.umn.edu/Research/GroupLens/index.html.
［20］	Yang Z H,Xu L,Cai Z M,et al.Re-scale AdaBoost for attack detection in collaborative filtering recommender systems［J］.Knowledge-Based Systems,2016,100:74-88.
［21］	Li Hong-bo,Peng San-cheng,Bai Jin-bo,et al.The analysis of a class of decision tree ID3 algorithms［J］.Software Guide,2016,15(2):30-32.(in Chinese)
［22］	Wei Xing-jun, Gu Qing-hua.Semi-supervised detection of shilling attack for recommender system based on character- istic index［J］.Application Research of Computers,2018,35(7):2185-2188.(in Chinese)
	附中文参考文献：
［13］	李文涛,高旻,李华,等.一种基于流行度分类特征的托攻击检测算法［J］.自动化学报,2015,41(9):1563-1576.
［16］	李聪,骆志刚.基于数据非随机缺失机制的推荐系统托攻击探测［J］.自动化学报,2013,39(10):1681-1690.
［21］	李泓波,彭三城,白劲波,等.一类决策树ID3改进算法探究［J］.软件导刊,2016,15(2):30-32.
［22］	卫星君,顾清华.基于特征指标推荐系统托攻击半监督检测［J］.计算机应用研究,2018,35(7):2185-2188.

[1]	王玫申, 张鹏, 薛乐洋, . 基于二分网络的长期推荐[J]. 计算机工程与科学, 2023, 45(04): 691-700.
[2]	罗可劲, 刘广聪, 杨文浩. 基于多任务学习的图神经网络推荐模型研究[J]. 计算机工程与科学, 2023, 45(04): 726-733.
[3]	邹程辉, 李卫疆, . 融合知识图谱和评论文本的个性化推荐模型[J]. 计算机工程与科学, 2023, 45(01): 181-190.
[4]	崔弘, 赵双, 张广胜, 苏金树. 基于机器学习的移动代理应用流量识别方法[J]. 计算机工程与科学, 2022, 44(04): 654-664.
[5]	吕成戍. 基于代价敏感支持向量机的推荐系统托攻击检测方法[J]. J4, 2014, 36(04): 697-701.