基于非对称半监督集成SVM的托攻击检测方法

doi:10.12005/orms.2018.0185

摘要/Abstract

摘要： 受推荐系统在电子商务领域重大经济利益的驱动,恶意用户以非法牟利为目的实施托攻击,操纵改变推荐结果,使推荐系统面临严峻的信息安全威胁,如何识别和检测托攻击成为保障推荐系统信息安全的关键。传统支持向量机(SVM)方法同时受到小样本和数据不均衡两个问题的制约。为此,提出一种半监督SVM和非对称集成策略相结合的托攻击检测方法。首先训练初始SVM,然后引入K最近邻法优化分类面附近样本的标记质量,利用标记数据和未标记数据的混合样本集减少对标记数据的需求。最后,设计一种非对称加权集成策略,重点关注攻击样本的分类准确率,降低集成分类器对数据不均衡的敏感性。实验结果表明,本文方法有效地解决了小样本问题和数据不均衡分布问题,获得了较好的检测效果。

关键词: 支持向量机, 非对称加权, 半监督集成, 托攻击检测, 信息安全

Abstract: Driven by the significant economic benefits of the recommendation system in the field of electronic commerce, malicious users implement shilling attacks for the purpose of illegal profit making, manipulate and change the recommendation results. Recommendation system faces major security threats, so how to detect shilling attacks becomes crucial to guarantee the security of recommender system. Shilling attack detection method based on traditional support vector machine is challenged by the small sample problem and the asymmetric distribution problems. This paper proposes an asymmetric ensemble method with semi-supervised SVM for detecting shilling attacks to address these problems. In the first stage, I use support vector machine (SVM) as the basic classifier, and in the second stage us KNN classifier to improve the quality of the new training examples which are transformed from the boundary vectors, and unlabeled data are presented to produce a number of semi-supervised classifiers. Then by the asymmetric semi-supervised ensemble strategies, these classifiers are combined .The ensemble classification model pays more attention to the positive samples than the negative ones. The proposed approach is applied to benchmark problems, and the simulation results show its validity.

Key words: support vector machine, asymmetric weighting, semi-supervised ensemble, shilling attack detection, information security

中图分类号:

TP309

吕成戍. 基于非对称半监督集成SVM的托攻击检测方法[J]. 运筹与管理, 2018, 27(8): 84-91.

LV Cheng-shu. Shilling Attack Detection Approach Based on Asymmetric Semi-supervised Ensemble SVM[J]. Operations Research and Management Science, 2018, 27(8): 84-91.

参考文献

[1] 许海玲,吴潇,李晓东.阎保平.互联网推荐系统比较研究[J].软件学报, 2009,20(2): 350-362.
[2] 伍之昂,王有权,曹杰.推荐系统托攻击模型与检测技术[J].科学通报,2014,56(7):551-560.
[3] VAPNIK V N.The nature of statistical learning theory[M].2nd ed.Germany:Springer,2000. 24-37.
[4] Burke R,Mobasher B,Williams C,et al.Detecting profile attacking in collaborative recommender systems[C].In Proceedings of the 8th IEEE International Conference on E-Commerce Technology and the 3rd IEEE International Conference on Enterprise Computing,E-Commerce and E-Services.USA:IEEE,2006.23-30.
[5] Burke R,Mobasher B,Williams C,et al.Classification features for attack detection in collaborative recommender systems[C]. In Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.USA:ACM,2006.542-547.
[6] Williams C,Mobasher B,Burke R.Defending recommender systems: detection of profile injection attacks[J].Service Oriented Computing and Applications,2007,1(3) : 157-170.
[7] Mobasher B, Burke R, Bhaumik R. Toward trustworthy recommender systems: An analysis of attack models and algorithm robustness[J]. ACM Transactions on Internet Technology, 2007, (4): 23-32.
[8] Hurley N, Cheng Z, Zhang M. Statistical Attack Detection[C]. In Proceedings of the Third ACM Conference on Recommender Systems. USA:ACM , 2009. 149-156.
[9] Mehta B,Nejdl W.Attack resistant collaborative filtering[C].Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval. Singapore: ACM, 2008.75-82.
[10] 于辉.协同过滤推荐系统用户概貌注入攻击检测研究[D]. 广州:华南理工大学, 2012. 21-78.
[11] Liu X, Nielek R, Wierzbicki A, et al. Defending imitating attacks in web credibility evaluation systems[C]. Proceedings of the 22nd International Conference on World Wide Web. Brazil: ACM, 2013. 1115-1122.
[12] Zhang Fuzhi, Zhou Quanqiang. HHT-SVM: An online method for detecting profile injectionattacks in collaborative recommender systems[J]. Knowledge-Based Systems, 2014, 65: 96-105.
[13] Karthikeyan P, Selvi ST , Neeraja G, et al. Prevention of shilling attack in recommender systems using discrete wavelet transform and support vector machine[C]. In Proceedings of the Eighth International Conference on Advanced Computing.India: IEEE, 2017. 113-145.
[14] Lam S, Reidl J. Shilling recommender systems for fun and profit [C]. Proceedings of 13th International Conference on World Wide Web.USA: ACM, 2004.393-402.
[15] Zhang Fuzhing, Zhou Quan qiang. A Meta-learning-based Approach for Detecting Profile Injection Attacks in Collaborative Recommender Systems[J]. Journal of Computers, 2012, 7(1): 226-234.
[16] 王丽娜.推荐攻击集成检测模型的概率输出方法研究[D].秦皇岛:燕山大学, 2015. 26-35.
[17] Lu Boli, Wang Xibin. Semi-supervised learning combining transductive support vector machine with active learning[J]. Neurocomputing, 2016, 173(3): 1288-1298.
[18] 吕成戍,王维国. 不均衡数据集下基于SVM的托攻击检测方法[J].计算机工程,2013, 39(5): 132-135.
[19] Zhou Wei, Wen Junhao, Gao Min.A Shilling Attack Detection Method Based on SVM and Target Item Analysis in Collaborative Filtering Recommender Systems[C]. The 8th International Conference on Knowledge Science,Engineering and Management. China: Springer, 2015, 751-763.
[20] 贾冬艳,张付志.基于双重邻居选取策略的协同过滤推荐算法[J].计算机研究与发展, 2013, 50(5) : 1076 -1084.
[21] Miller B N, Albert I, Lam S K, et al. MovieLens unplugged: Experiences with an occasionally connected recommender system[C]. Proceedings of the International Conference on Intelligent User Interfaces. USA: ACM Press, 2003, 263-266.