평가 스트림 추세 분석을 이용한 추천 시스템의 공격 탐지 = Attack Detection in Recommender Systems Using a Rating Stream Trend Analysis

다국어 초록 (Multilingual Abstract)

The recommender system analyzes users` preference and predicts the users` preference to items in order to recommend various items such as book, movie and music for the users. The collaborative filtering method is used most widely in the recommender system. The method uses rating information of similar users when recommending items for the target users. Performance of the collaborative filtering-based recommendation is lowered when attacker maliciously manipulates the rating information on items. This kind of malicious act on a recommender system is called `Recommendation Attack`. When the evaluation data that are in continuous change are analyzed in the perspective of data stream, it is possible to predict attack on the recommender system. In this paper, we will suggest the method to detect attack on the recommender system by using the stream trend of the item evaluation in the collaborative filtering-based recommender system. Since the information on item evaluation included in the evaluation data tends to change frequently according to passage of time, the measurement of changes in item evaluation in a fixed period of time can enable detection of attack on the recommender system. The method suggested in this paper is to compare the evaluation stream that is entered continuously with the normal stream trend in the test cycle for attack detection with a view to detecting the abnormal stream trend. The proposed method can enhance operability of the recommender system and re-usability of the evaluation data. The effectiveness of the method was verified in various experiments.

참고문헌 (Reference)

1 G. Adomavicius, "Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions" 17 (17): 734-749, 2005

2 U. Shardanand, "Social Information Filtering: Algorithms for Automating 'Word of Mouth'" 1995

3 S. Lam, "Shilling Recommender Systems for Fun and Profit" 2004

4 J. Schafer, "Recommender System in E-Commerce" 1999

5 A. Poposcul, "Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments" 2001

6 P. Chirita, "Preventing Shilling Sttacks in Online Recommender Systems" 2005

7 R. Burke, "Limited Knowledge Shilling Attacks in Collaborative Filtering Systems" 2005

8 B. Sarwar, "Item-based Collaborative Filtering Recommendation Algorithms" 2001

9 J. O’Donovan, "Is Trust Robust?: An Analysis of Trust-based Recommendation" 2006

10 C. Dellarocas, "Immunizing Online Reputation Reporting Systems against Unfair Ratings and Discriminatory Behavior" 2000

11 J. Konstan, "GroupLens: Applying Collaborative Filtering to Usenet News" 40 (40): 77-87, 1997

12 H. Kim, "Feature-Based Prediction of Unknown Preferences for Nearest-Neighbor Collaborative Filtering" 2004

13 J. Herlocker, "Evaluating Collaborative Filtering Recommender Systems" 1-, 2004

14 B. Mobasher, "Effective Attack Models for Shilling Item-based Collaborative Filtering Systems" 2005

15 P. Melville, "Content-Boosted Collaborative Filtering" 2001

16 M. O’Mahony, "Collaborative Recommendation: A Robustness Analysis" 4 (4): 2004

17 R. Burke, "Classification Features for Attack Detection in Collaborative Recommender Systems" 2006

18 M. Condliff, "Baysian Mixed-Effect Models for Recommender Systems" 1999

19 J. Herlocker, "An Algorithmic Framework for Performing Collaborative Filtering" 1999

20 G. Linden, "Amazon.com Recommendations: Item-to Item Collaborative Filtering" 2003

21 M. Pazzani, "A Framework for Collaborative, Content-based and Demographic Filtering" 393-408, 1999