Change search
ReferencesLink to record
Permanent link

Direct link
Semi-SAD: Applying semi-supervised learning to shilling attack detection
KTH, School of Architecture and the Built Environment (ABE), Urban Planning and Environment, Geodesy and Geoinformatics.
2011 (English)In: RecSys - Proc. ACM Conf. Recomm. Syst., 2011, 289-292 p.Conference paper (Refereed)
Abstract [en]

Collaborative filtering (CF) based recommender systems are vulnerable to shilling attacks. In some leading e-commerce sites, there exists a large number of unlabeled users, and it is expensive to obtain their identities. Existing research efforts on shilling attack detection fail to exploit these unlabeled users. In this article, Semi-SAD, a new semi-supervised learning based shilling attack detection algorithm is proposed. Semi-SAD is trained with the labeled and unlabeled user profiles using the combination of naïve Bayes classifier and EM-λ, augmented Expectation Maximization (EM). Experiments on MovieLens datasets show that our proposed Semi-SAD is efficient and effective.

Place, publisher, year, edition, pages
2011. 289-292 p.
, RecSys'11 - Proceedings of the 5th ACM Conference on Recommender Systems
Keyword [en]
em, naïve bayes, semi-supervised learning, shilling attack detection, Attack detection, Bayes Classifier, Collaborative filtering, Data sets, E-commerce sites, Expectation Maximization, Research efforts, User profile, Recommender systems, Supervised learning
National Category
Information Systems
URN: urn:nbn:se:kth:diva-150656DOI: 10.1145/2043932.2043985ScopusID: 2-s2.0-82555183087ISBN: 9781450306836OAI: diva2:746286
5th ACM Conference on Recommender Systems, RecSys 2011, 23-27 October 2011, Chicago, IL. USA

QC 20140912

Available from: 2014-09-12 Created: 2014-09-08 Last updated: 2014-09-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Mao, Bo
By organisation
Geodesy and Geoinformatics
Information Systems

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 18 hits
ReferencesLink to record
Permanent link

Direct link